{"as_of":"2026-08-15T16:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1ab0d9b1c2ba0f8fbc22270dbe56b87fcb3315a19f950645b4dbdb183c07c278","coverage":[{"denominator":299,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T13:05:53.524314Z","state":"measured"},{"denominator":102,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":102,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T21:35:43.540653Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T21:46:40.706675Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.10444","snapshot_observed_at":"2026-08-06T21:35:43.540653Z","title":"A survey of represen- tation learning, optimization strategies, and applications for omnidirectional vision","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.23897","last_updated":"2025-07-03T12:44:27Z","snapshot_observed_at":"2026-08-12T06:05:17.434622Z","submitted_at":"2025-06-30T14:30:25Z","title":"PriOr-Flow: Enhancing Primitive Panoramic Optical Flow with Orthogonal View","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T21:35:43.540653Z"},"links":{"cited_paper":"/paper/2502.10444","citing_paper":"/paper/2506.23897"},"observation_digest":"sha256:1c449b38a59673a5e87c762523bf025b0b1bbb897ea41ab5998fcaa80289cc98","observation_id":"64d754d0-8896-4367-af99-88402a3480ba","resolution":{"observed_at":"2026-08-06T21:35:43.540653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"cited_work":{"arxiv_id":"2502.10444","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.10444","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A survey of representation learning, optimization strategies, and applications for omnidirectional vision.arXiv preprint arXiv:2502.10444","venue":null,"work_id":"19e08802-2c0e-4c77-80f6-4dcc9177a99c","year":null},"citing_paper":{"arxiv_id":"2604.24642","last_updated":"2026-04-27T16:10:00Z","snapshot_observed_at":"2026-08-11T10:42:18.680287Z","submitted_at":"2026-04-27T16:10:00Z","title":"Probing CLIP's Comprehension of 360-Degree Textual and Visual Semantics","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-08T04:25:58.275705Z"},"links":{"cited_paper":"/paper/2502.10444","citing_paper":"/paper/2604.24642"},"observation_digest":"sha256:1162277e8b93edd4b17caceb3c42186bfe2c77b57525c33e9275fc0b0373d7d3","observation_id":"6bc52420-93c5-4444-9a6a-115f2b9ff4e3","resolution":{"observed_at":"2026-05-11T21:46:40.726462Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.10444/citation-record","integrity":"/paper/2502.10444/integrity","json":"/paper/2502.10444/citation-record.json","paper":"/paper/2502.10444"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.145212Z","title":"O’Connor","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.145212Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:2986047b60556a3bd33e5ed7ee8541f4db00f7cf07f2b5ed5967b762712f13b6","observation_id":"a7596587-3382-437b-8034-2556539d20d3","resolution":{"observed_at":"2026-08-08T13:05:53.145212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.149730Z","title":"Hrdfuse: Monocular 360 depth estimation by collab- orativelylearningholistic-with-regionaldepthdistributions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.149730Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:e47d7675fe7104ff69b028e616cfae38e2c7f0b596b063e8cf259aee07957fc8","observation_id":"291e385f-ccdf-4303-8af6-2244222c0090","resolution":{"observed_at":"2026-08-08T13:05:53.149730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.154092Z","title":"Lu, Chen Chen, Jiancang Ma, Pengyuan Zhou, Tae-Kyun Kim, Pan Hui, and Lin Wang","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.154092Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:ec32b5cceb408b694a1f89271a628fca42c2ea7c108d477bbab533c85c018bc2","observation_id":"ebcda7b5-a942-4695-979e-1300735432b4","resolution":{"observed_at":"2026-08-08T13:05:53.154092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.158261Z","title":"360-degree image completion by two- stage conditional gans","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.158261Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:cd1a3f54f6045fc53700156bc78bb9e8a9fa0e158b87ac165d6dbbd3830a972e","observation_id":"2d4c5d58-e771-4302-bcd6-59e0c228fd36","resolution":{"observed_at":"2026-08-08T13:05:53.158261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.162641Z","title":"Diverse plausible 360-degree image outpainting for efficient 3dcg background creation.CVPR, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.162641Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:8f4618512056f0a9c404594fc95a24f8442be2ba5a89d0bd17273332fbd60327","observation_id":"b7f00fb1-f3dd-4dad-9e48-e4b0f26df949","resolution":{"observed_at":"2026-08-08T13:05:53.162641Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.166669Z","title":"Gkitsas, Vladimiros Sterzentsenko, et al","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.166669Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:0a3f71028e1c3244e218c50c6a4339b900ba81bfcabb18a2720c1a488e7823e0","observation_id":"dffa1998-734d-42ee-adcb-c9852f96ede8","resolution":{"observed_at":"2026-08-08T13:05:53.166669Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.09004","last_updated":"2018-05-22T07:01:30Z","snapshot_observed_at":"2026-08-14T19:22:33.932732Z","submitted_at":"2018-04-24T13:08:39Z","title":"Cubes3D: Neural Network based Optical Flow in Omnidirectional Image Scenes","version":2},"cited_work":{"arxiv_id":"1804.09004","doi":null,"metadata_source":"pith","pith_arxiv_id":"1804.09004","snapshot_observed_at":"2026-08-08T13:05:54.289378Z","title":"Cubes3D: Neural Network based Optical Flow in Omnidirectional Image Scenes","venue":"cs.CV","work_id":"b8e2e71c-0a2b-4f4a-8d95-ae5ab8e568b9","year":2018},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.171067Z"},"links":{"cited_paper":"/paper/1804.09004","citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:60e557bbe7180ef5f0fda4d80dcb3b5f6972762a96641c0e3b3abeca4d8b1296","observation_id":"e849452a-22d4-4e4e-8793-815c8e1b694a","resolution":{"observed_at":"2026-08-08T13:05:54.295706Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.175677Z","title":"Joint 2d-3d-semantic data for indoor scene understanding","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.175677Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:16b1e2d4cb9cb0394524d9cfad344ee0a95d03cd0231ef2106c726cc4d6a3612","observation_id":"ab02fbc5-1e26-4b79-b7b0-21b8ac466f71","resolution":{"observed_at":"2026-08-08T13:05:53.175677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.179564Z","title":"Omniflownet: a perspective neural network adaptation for optical flow estimation in omnidirectional images","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.179564Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:686ddc1bd147fe907703d0c201cdc83b0cfcd37e9d713feb46607083f2751efc","observation_id":"51c9d6a3-9c56-44d7-8df0-036c5bcb79cd","resolution":{"observed_at":"2026-08-08T13:05:53.179564Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.183377Z","title":"Glpanodepth: Global-to-local panoramic depth estimation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.183377Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:674b7479f76f4772f0b1618686cae2a427c2aeabce7ad59000b59f2426f05ca8","observation_id":"ec883056-f08b-404e-be01-6fa7585b69f5","resolution":{"observed_at":"2026-08-08T13:05:53.183377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.187137Z","title":"Ma360: Multi-agent deep rein- forcement learning based live 360-degree video streaming on edge","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.187137Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:62868e4d59688e35b56b1fa1e76e671050f9d9cb5e96030eaaf47a20ea82a044","observation_id":"b2b1550a-5ba3-4d59-a40c-e36c014f7f27","resolution":{"observed_at":"2026-08-08T13:05:53.187137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.191109Z","title":"Multidiffusion: Fusing diffusion paths for controlled image generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.191109Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:2eb59500a2091cdecb454236f75f52529611a2654512aef10a59c5d74f4cc6bb","observation_id":"069441bd-7a43-47cc-b4a5-57ac9520c449","resolution":{"observed_at":"2026-08-08T13:05:53.191109Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.194647Z","title":"On the use of deep learning for computational imaging","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.194647Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:e2035dbf868cdf7600c05858084dfc7e628ddce761aa9adedcc11e1bee5a5924","observation_id":"6fe65f2f-551d-442a-9e6b-0678d6b2cf46","resolution":{"observed_at":"2026-08-08T13:05:53.194647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.198395Z","title":"To- wards autonomous driving: a multi-modal 360◦ perception proposal","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.198395Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:40b3df508f5c01e173c4a305925f2d1ff5259492d1991d44e31749f564702b8f","observation_id":"777990cb-5640-4783-a545-7b9e9690f71c","resolution":{"observed_at":"2026-08-08T13:05:53.198395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.201899Z","title":"Scaled 360 layouts: Revisiting non-central panoramas","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.201899Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:010afbc763c2256dc212f33eae936a0b76075f263cd427f82f71b55a5d8163fa","observation_id":"a4e079d9-43b3-4d9d-b7cc-6f8e6f251d3b","resolution":{"observed_at":"2026-08-08T13:05:53.201899Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.205558Z","title":"Atlanta scaled layouts from non-central panoramas","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.205558Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:09aa59277dd822a8cf4348ad533f3929f2bc90b26f4f8a25e61ef9a2ece9e7a0","observation_id":"a8309acf-7a0d-49c9-8e61-43aba12837db","resolution":{"observed_at":"2026-08-08T13:05:53.205558Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.209174Z","title":"Learning omnidirectional flow in 360◦ video via siamese representation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.209174Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:2af5442b7bb6bb800fa548dcc49c0a4fc439bc952f30479b7cdf2247ff23d36b","observation_id":"365164c5-f8da-439a-9d5d-415e4f8ab7d9","resolution":{"observed_at":"2026-08-08T13:05:53.209174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.213118Z","title":"Revisiting optical flow estimation in 360 videos","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.213118Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:1a6ca370991878b191805af71a7b52f2a4ee6d86354def125fcfdf6319214d40","observation_id":"7f45949a-9c2a-4ddc-9b9a-63a77d190aaf","resolution":{"observed_at":"2026-08-08T13:05:53.213118Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.216838Z","title":"nuscenes: A multi- modal dataset for autonomous driving","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.216838Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:35f6b2878d89e07d1149c92b04fa714d88419236fb40318ab50e2ac02389a815","observation_id":"b7b1999d-f06d-4adc-8697-d618099b4d09","resolution":{"observed_at":"2026-08-08T13:05:53.216838Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.220552Z","title":"Field- of-view iou for object detection in 360° images","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.220552Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:df296a189ae05ca2a7366d939b2bf12ec38847633dea9753d322c62265444e37","observation_id":"71f744dd-c1c7-4a5f-9cb1-e5eb509e3a71","resolution":{"observed_at":"2026-08-08T13:05:53.220552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.224366Z","title":"Ntire 2023 challenge on 360° omnidirectional image and video super-resolution: Datasets, methods and results.CVPR Workshop, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.224366Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:67ac1586ce4c9c0501d02be1a6c572c6d52d2156e54389e8e82b9d3215d7e37c","observation_id":"7caf2b79-c714-4e43-a5f1-3a1328afd684","resolution":{"observed_at":"2026-08-08T13:05:53.224366Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.228079Z","title":"Omnizoomer: Learning to move and zoom in on sphere at high-resolution","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.228079Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:fc65b2f2f25d42919a1899c6803ac7b7764d408983559653240bf3c2ac912509","observation_id":"3e18cffb-71f9-417d-a9e9-dfc044f8e411","resolution":{"observed_at":"2026-08-08T13:05:53.228079Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.231899Z","title":"Engel, and Daniel Cremers","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.231899Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:17762230c23684fe1cd137c50b13e2bac33844e40ac7aa0693904194f8a64e5a","observation_id":"72995053-477c-460e-8430-856b7744e544","resolution":{"observed_at":"2026-08-08T13:05:53.231899Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.234859Z","title":"Blind quality assessment of omnidirectional videos using spatio-temporal convolutional neural networks.Optik, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.234859Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:a3e3bf3c1de22752cfa55f082711ed373a8ece96f58746ed6898c4fa21ec4563","observation_id":"a399c09e-3dd3-4af7-9d36-bbf1a49d3a24","resolution":{"observed_at":"2026-08-08T13:05:53.234859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.238196Z","title":"Matterport3d: Learning from rgb-d data in indoor environments.ArXiv, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.238196Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:19193b3f300eba342d64bd28e14070fdb0e83a14a4bfc425fb52d4425af2de17","observation_id":"a278ffbd-0de3-4945-a5c1-d5872a672d5a","resolution":{"observed_at":"2026-08-08T13:05:53.238196Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.241934Z","title":"Generating 360 outdoor panorama dataset with reliable sun position estimation.SIGGRAPH Asia 2018 Posters, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.241934Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:d70e8240180a6d202e3019c6f9f0b088dd25cb100a015e31fd975635b7f0cbf5","observation_id":"7c44cae2-4552-42d8-a656-757e9a02a262","resolution":{"observed_at":"2026-08-08T13:05:53.241934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.245080Z","title":"Depth estimation from indoor panoramas with neural scene repre- sentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.245080Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:b7013dd2e8bc5441c470e5af7e60f505312fb3b97eeb12d8b67c6cb8e1a57de9","observation_id":"a42b3a78-586e-4e62-b792-045b6becd653","resolution":{"observed_at":"2026-08-08T13:05:53.245080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.248469Z","title":"Borgwardt","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.248469Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:b18a19487821d42b4bc487a50acf0e1ccf80761f89ec24e951b8b0f3f47ece1f","observation_id":"4d1c972c-64d0-464e-a965-aae7dc3891a5","resolution":{"observed_at":"2026-08-08T13:05:53.248469Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.251656Z","title":"Intra- and inter- reasoning graph convolutional network for saliency predic- tion on 360° images","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.251656Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:3206251d14cdfda6e89e15e43bbaadbcd944161b002a711ceab111bff41afcf3","observation_id":"ae2a4c47-fc94-4840-a208-54d85decf43c","resolution":{"observed_at":"2026-08-08T13:05:53.251656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.254794Z","title":"Salbinet360: Saliency prediction on 360◦ images with local-global bifurcated deep network.IEEE VR, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.254794Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:81c649edf61bb828e70a679c5939fe124989c2075abb640c961f6e57a83e0198","observation_id":"2c448ab2-d1d1-4af7-99c4-bb0919a4722c","resolution":{"observed_at":"2026-08-08T13:05:53.254794Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.258303Z","title":"Multi-stage salient object detection in 360° omnidirectional image using complementary object-level semantic information","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.258303Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:031f6dce861fecb6649ab6711c7bea7c2122f0d0b85139f40af295ebf0c198f7","observation_id":"c27b4f59-fecc-48d6-9511-1db21d9cc547","resolution":{"observed_at":"2026-08-08T13:05:53.258303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.261405Z","title":"360+ x: A panoptic multi- modal scene understanding dataset","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.261405Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:89f721f35780587a5f909180e61a63697b6928de0a2e6aed80145fb5c24729d3","observation_id":"8829e719-2453-4788-8205-abb3e07863d5","resolution":{"observed_at":"2026-08-08T13:05:53.261405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.264951Z","title":"Dif- fusiondet: Diffusion model for object detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.264951Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:cc3c68b51cc57725353bda8ee0285f3b9e6932bb32cd09c9e906a522b7514c4e","observation_id":"5294ba22-4b9a-43d6-9899-359100f30ba2","resolution":{"observed_at":"2026-08-08T13:05:53.264951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.268698Z","title":"Spherical structural similarity index for objective omnidirectional video quality assessment.ICME, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.268698Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:6816a6b0616acec814fc7b3e6c0d595bf9674b66ec52c80f22c73435ac920039","observation_id":"424cf520-5f63-44b7-ad90-c122d3169d96","resolution":{"observed_at":"2026-08-08T13:05:53.268698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.272634Z","title":"Dynamic convolution: Attention over convolution kernels.CVPR, pages 11027– 11036, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.272634Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:57a50046a03ea7182d3cbe6540a9807b38f3ce5700ad51e3d05e7152ee638d6c","observation_id":"8c4816ce-0ea7-4e19-a122-026ab6207b46","resolution":{"observed_at":"2026-08-08T13:05:53.272634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.276240Z","title":"A unified and biologically-plausible re- lational graph representation of vision transformers.IEEE TNNLS, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.276240Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:d0ad65589f8a4ab440fa7f376f60419557a5cefe080773a5b7fd20c949552e11","observation_id":"a344619e-2c83-4123-b59d-d1345100d399","resolution":{"observed_at":"2026-08-08T13:05:53.276240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.279573Z","title":"Text2light: Zero-shot text-driven hdr panorama generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.279573Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:34765553dc0088fc9eb3956c69bdda4ef161fb2cb4884f1d4f459e0c438c1a25","observation_id":"b7ae3e0a-63ac-43b4-9b90-77f36f11416c","resolution":{"observed_at":"2026-08-08T13:05:53.279573Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.283016Z","title":"Recent advances in omnidirectional video coding for virtual reality: Projection and evaluation.Signal Process., 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.283016Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:343ec14051c48fe5df22f161dbf3289249fbb126657bb6c88a9609813ef4e5ba","observation_id":"d558b13b-fad2-4e3f-bc21-47a9dc9802ac","resolution":{"observed_at":"2026-08-08T13:05:53.283016Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.286396Z","title":"Unsupervised omnimvs: Efficient omnidirectional depth inference via establishing pseudo-stereo supervision","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.286396Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:3d498655cde288f3ac272047232d15a0668dbbb4f7c892ec3be266550c9e50a2","observation_id":"9bcc4943-3224-4df1-9b33-96734cad1e1a","resolution":{"observed_at":"2026-08-08T13:05:53.286396Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.289889Z","title":"Cube padding for weakly-supervised saliency prediction in 360 videos","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.289889Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:ecab3e9f42fb3ccad57745c0865d42836b608a53af6f08cad3cf6e9e3cce6f18","observation_id":"0ba5ee34-4175-40b4-b437-5c9fcf23f66d","resolution":{"observed_at":"2026-08-08T13:05:53.289889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.293339Z","title":"Sam- pling based spherical transformer for 360 degree image classification","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.293339Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:3ba4541337e76562bc9b17286f3cdc17c934c6e1ebefcae0a08eb7603ad965b1","observation_id":"24d799ba-f6e4-4499-a0ea-f74e864588e9","resolution":{"observed_at":"2026-08-08T13:05:53.293339Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.297175Z","title":"360-indoor: towards learn- ing real-world objects in 360deg indoor equirectangular images","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.297175Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:dd48f0c25ff7fed590ca97967a945796a731a167195242520af93fb4f1e21842","observation_id":"14536c13-5584-48fd-9cd8-f1a966f64bfc","resolution":{"observed_at":"2026-08-08T13:05:53.297175Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.300866Z","title":"Gauge equivariant convolutional networks and the icosahedral cnn","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.300866Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:cea1c4125aa5f8537094c6f6e8ee36a8d0c14fdef72f64edee1feaa1e0c6e607","observation_id":"b6750630-d0e2-4395-80dc-33dfecb5208c","resolution":{"observed_at":"2026-08-08T13:05:53.300866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.304873Z","title":"Group equivariant convolu- tional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.304873Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:753b520e29508bd64f63f0bd1d38b272477f4ab8583d1c1dd1ea6dd0af09c41e","observation_id":"96be58f7-4ff1-4656-be3e-f25c03c62a5a","resolution":{"observed_at":"2026-08-08T13:05:53.304873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.308646Z","title":"Spherenet:Learningsphericalrepresentations for detection and classification in omnidirectional images","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.308646Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:751f7a27f205619018f79c809e10635d78b9b7efc9e1472fc92795fd3c64874c","observation_id":"ba83437a-c9dd-4733-b438-411a49931c69","resolution":{"observed_at":"2026-08-08T13:05:53.308646Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.312075Z","title":"Coughlan and Alan Loddon Yuille","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.312075Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:8158723473e7348267af688cae1e5a276ac20ab3ddb60e4c638b0d9373e157ad","observation_id":"44acf6fd-b307-4eb2-84ab-57224315cdf5","resolution":{"observed_at":"2026-08-08T13:05:53.312075Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.315974Z","title":"Zillow indoor dataset: Annotated floor plans with 360deg panoramas and 3d room layouts","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.315974Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:6432abb0e4065ecefb55d5586052f03657aca67114b8a6b32531365088029e77","observation_id":"23a47053-529f-4661-ab99-ea1ea3ed37ad","resolution":{"observed_at":"2026-08-08T13:05:53.315974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.319810Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.319810Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:fb3b5751ba8b8e790c774d5489c5616416197108e3a0ec936d78dd9114202263","observation_id":"6022e44f-4842-4cba-b2e5-1cbb6fa164df","resolution":{"observed_at":"2026-08-08T13:05:53.319810Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.323574Z","title":"Dilated convolutional neural networks for panoramic image saliency prediction.ICASSP, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.323574Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:eeced2fd88401df69b224e2b2858eb303b9f60444d715a6d6af825bdf49f52ac","observation_id":"fe58dadc-8726-4937-a008-0d2bdd7ed8f4","resolution":{"observed_at":"2026-08-08T13:05:53.323574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.327978Z","title":"Guided co-modulated gan for 360° field of view extrapolation.3DV, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.327978Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:2f52460b54a2ef85f3806b28fda10300e1eb07d8c0d5d9455c99ed8560403270","observation_id":"8c6547b3-b393-49aa-92fa-de69eb51969c","resolution":{"observed_at":"2026-08-08T13:05:53.327978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.331970Z","title":"Ev- erlight: Indoor-outdoor editable hdr lighting estimation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.331970Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:bc37c55c22c6cb5077adf8335e3bb574b43e56c79fb7a4f85edf8f62d6c9009a","observation_id":"06eb41b8-1aaa-4665-b523-1bf9d64e1da3","resolution":{"observed_at":"2026-08-08T13:05:53.331970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.335740Z","title":"A viewport-driven multi-metric fusion approach for 360- degree video quality assessment.ICME, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.335740Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:ff38167184c42ba0087db6d0f991fc23dd5ff0d940cae131402475dbf233cfcb","observation_id":"a967e438-e66f-40a3-a573-2363374f2b2f","resolution":{"observed_at":"2026-08-08T13:05:53.335740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.339801Z","title":"Saliency prediction for omnidirectional images considering optimization on sphere domain.ICASSP, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.339801Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:e20114bef3ab87651f873cc1d349bbb75c356fc1f8767017626283572dc75bda","observation_id":"bceee0d4-7407-4d3e-942e-dd9fa4487e9a","resolution":{"observed_at":"2026-08-08T13:05:53.339801Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.343573Z","title":"Deepsphere: a graph-based spherical cnn","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.343573Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:554ed6ca1722ec4600cbcfb6ace4c482b9d998dc03b64619fc5d73ab9c8c2305","observation_id":"cfd94bc5-b473-4583-8b5d-cbcc0ea4d75d","resolution":{"observed_at":"2026-08-08T13:05:53.343573Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.347407Z","title":"The mnist database of handwritten digit images for machine learning research","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.347407Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:344e8d8d7b10535e53c5c677cc49e70359ba54cc2274406ad49a629843bf3e51","observation_id":"ad86ece0-ff45-4115-b24b-09f8b904ec87","resolution":{"observed_at":"2026-08-08T13:05:53.347407Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.351176Z","title":"Restricted deformable convolution- based road scene semantic segmentation using surround view cameras","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.351176Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:1d2be8a7635f87f180203ba993462c501ddab664ed7032bf6056b0d718b0e667","observation_id":"feade347-bd0e-4ab9-b810-68cd56404e08","resolution":{"observed_at":"2026-08-08T13:05:53.351176Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.354729Z","title":"Cnn based semantic segmentation for urban traffic scenes using fisheye camera.IV, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.354729Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:ea2ebbce889535300bb17656b02442a8450b22f382b9816b5b6779b7e17a072f","observation_id":"f9f301ac-79e2-4ef5-9cb9-eb49059755b0","resolution":{"observed_at":"2026-08-08T13:05:53.354729Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.358627Z","title":"Lau-net: Latitude adaptive upscaling network for omnidirectional imag super-resolution.CVPR, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.358627Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:fc6272a612002c29bd802f55292bdbb6e64ec0fe3a3cbfb7ef81afbedd4d6331","observation_id":"9a594569-1ffe-4955-a661-f5c2cffc96fc","resolution":{"observed_at":"2026-08-08T13:05:53.358627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.362270Z","title":"Extending 2d saliency models for head movement prediction in 360-degree images using cnn- based fusion","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.362270Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:622737d804bf5800a00b9193354454534527931b07f6414dcefd29cec4944007","observation_id":"89482050-99ab-4448-9709-c995fd08b180","resolution":{"observed_at":"2026-08-08T13:05:53.362270Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.365960Z","title":"Panocontext-former: Panoramic total scene understanding with a transformer.ArXiv, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.365960Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:2b279435ffede8aaa195d7cae2e9cc63d6f927c83f7956da6c0ce6b287489852","observation_id":"7cbc36b8-6cca-48ba-ab8f-14c580e390ed","resolution":{"observed_at":"2026-08-08T13:05:53.365960Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.369674Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale.ICLR, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.369674Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:33f58e8d86dc8d0a379d5ed9d1bda42ae2627cc1c8c7af16c6a60e6365774834","observation_id":"bea55e35-5e11-44d0-8be3-9640c41e6347","resolution":{"observed_at":"2026-08-08T13:05:53.369674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.373351Z","title":"Perceptual quality assessment of omnidirectional images.ISCAS, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.373351Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:74a4a9c81be9c57fe95c76fc3aea4a95b122f6d6c3a678e74e2fbad1fa7201d3","observation_id":"579b09e0-c666-4ac3-b0ed-d5ea66d1c811","resolution":{"observed_at":"2026-08-08T13:05:53.373351Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.377127Z","title":"Pano popups: Indoor 3d reconstruction with a plane-aware network","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.377127Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:1b78dfe5803258d2804f1b2a654156a8e14901ab32c6bcbe6f51e5c60ccb4970","observation_id":"d6e424ff-0ef8-4c3a-b05c-a14115262856","resolution":{"observed_at":"2026-08-08T13:05:53.377127Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.380734Z","title":"Tangent images for mitigating spherical distortion","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.380734Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:7ecc82b2c1beac33ae591cb721740211bdafcfa5e27b7d0de43146983b5f7fe2","observation_id":"40f0460f-17dd-4beb-8ea5-fbf2f9699705","resolution":{"observed_at":"2026-08-08T13:05:53.380734Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.385057Z","title":"Engel, Thomas Schöps, and Daniel Cremers","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.385057Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:f3cbef62166749d99d5a8c0b7b5436a6449b5aac0ddcc584d0951ac63b7d2dcd","observation_id":"658943ff-7e48-4bca-a86d-93d571034e80","resolution":{"observed_at":"2026-08-08T13:05:53.385057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.389092Z","title":"Taming transformers for high-resolution image synthesis.CVPR, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.389092Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:647381a7ec0f9842ff3437ed485d449bb6ac42d6e83f0519f8e8afe2b1e3da3e","observation_id":"59f213eb-d7d7-4218-9e96-88deeb09ee5b","resolution":{"observed_at":"2026-08-08T13:05:53.389092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.392955Z","title":"Deep depth estimation on 360 images with a double quaternion loss","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.392955Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:df0aa9c7615a0eac23d6b89d1dde1f53f945fc8e4e9ab820317e8291e9b4a147","observation_id":"42a152d3-8d7f-47c3-b762-ebf7a2dcaab6","resolution":{"observed_at":"2026-08-08T13:05:53.392955Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.397270Z","title":"360 depth estimation in the wild-the depth360 dataset and the segfuse network","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.397270Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:d54c666cda9606f76a62ffae1ec9bfa24bee559eff242dabd9dde0907ef1506c","observation_id":"ff80728d-7d91-47a1-b4a5-71b026e3b5a5","resolution":{"observed_at":"2026-08-08T13:05:53.397270Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.402345Z","title":"Fácil, Alejandro Pérez- Yus, Cédric Demonceaux, Javier Civera, and Josechu J","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.402345Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:a1a9a2632af7e455daed72429cad2611997b89d133cd631e90ac84f0d32be582","observation_id":"3f6cb845-f05e-4810-9be0-a40f9423dfe0","resolution":{"observed_at":"2026-08-08T13:05:53.402345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.405889Z","title":"Layouts from panoramic images with geometry and deep learning.RAL, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.405889Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:004ccc0f691b02a6ff5f1df6d0bfed49401e62466fc30b060c53cb3ed6e6925f","observation_id":"9c88710d-5dba-4a67-aa7f-e5be8f6ba6cd","resolution":{"observed_at":"2026-08-08T13:05:53.405889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.410966Z","title":"Generating a full spherical view by modeling the relation between two fisheye images.The Visual Computer, pages 1–26, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.410966Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:0a2b45b0038693df462a7174e849c3df5843fba67ff905dde6d77d842d3a7bd7","observation_id":"8515eb28-008b-41fd-a91d-b41ec2ff51a7","resolution":{"observed_at":"2026-08-08T13:05:53.410966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.415226Z","title":"Adaptive hypergraph convolutional network for no-reference 360-degree image quality assessment.ACM MM, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.415226Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:92ccd51e343344f71604d878e69d9d1bebcf5861fdb15528d1d36ee0da5fc9ae","observation_id":"676e87bc-b39d-48a5-a581-d244f9f4d818","resolution":{"observed_at":"2026-08-08T13:05:53.415226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.418902Z","title":"Quality assessment for omnidirectional video: A spatio-temporal distortion modeling approach.TMM, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.418902Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:efb1a754e1f0267440f577b938d7df5df347942277e2d50eca4350e63db2aa21","observation_id":"4d631b2b-cfa5-4e15-9afb-4b2bc930bcf3","resolution":{"observed_at":"2026-08-08T13:05:53.418902Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.422352Z","title":"Review on panoramic imaging and its appli- cations in scene understanding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.422352Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:29067cce0772cbb52e6b4fcc3571afc9f5595f8e301801b188fd5ea30bb37a00","observation_id":"b29eec47-8f33-4979-8186-48fc013fa127","resolution":{"observed_at":"2026-08-08T13:05:53.422352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.426560Z","title":"Deep parametric indoor lighting estimation.ICCV, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.426560Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:60124cd7962c9c93695b8f1cb7ac884011463577e212a79fd23d3f12df73b414","observation_id":"774a3d10-1012-4ac8-be59-63f314833527","resolution":{"observed_at":"2026-08-08T13:05:53.426560Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.429889Z","title":"Learning to predict indoor illumination from a single image.TOG, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.429889Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:e51766ab21c5ce14be49615b2ec417f2508adfd69a7d33f2d1dc704132c25341","observation_id":"a8d758e4-c65e-4f1b-a82b-c193763b2aec","resolution":{"observed_at":"2026-08-08T13:05:53.429889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.435437Z","title":"Carr, and Jean-François Lalonde","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.435437Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:c17240cc05755a8fdfe3810b90249ec6b54fe4560adc9b1df1d48fd174b3aef8","observation_id":"6ca85f34-5c07-483a-9e97-bd114b2253db","resolution":{"observed_at":"2026-08-08T13:05:53.435437Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.439219Z","title":"Generative adversarial nets.NIPS, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.439219Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:fe8cfa28798b1962bc136d6708088dab025366c91a6544d26444c1650b8f72e8","observation_id":"36e8e4e8-58a5-49c4-a5f9-a34bd4b88125","resolution":{"observed_at":"2026-08-08T13:05:53.439219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.442958Z","title":"Gorski, Eric Hivon, A","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.442958Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:c3ccf198f67f1af2e5e28547b4a11db9b50e1d7a07671f5912ab33df2cb90253","observation_id":"10b98e1a-6b44-4190-8620-a8ff72d2b323","resolution":{"observed_at":"2026-08-08T13:05:53.442958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.447782Z","title":"Zero-shot learning for reflection removal of single 360-degree image","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.447782Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:10a235053174fea93418d45b03c830bef9ebc21ac0d6f87d6f9ca92c441ad003","observation_id":"e65e96b3-a9ac-4a2f-ab79-c6b25b2a6ccc","resolution":{"observed_at":"2026-08-08T13:05:53.447782Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.451729Z","title":"Piinet: A 360-degree panoramic image inpainting network using a cube map","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.451729Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:db0b6ee2738156a9759959f6b2cf273abd601338ba707eb1e4a100492fdee3c8","observation_id":"7bba81c5-66b8-4cd4-a116-f47e9072491b","resolution":{"observed_at":"2026-08-08T13:05:53.451729Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.455420Z","title":"Enhancement of novel view synthesis using omnidirectional image completion","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.455420Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:a6b759cb3486662d12a3a7cdcbdcb01d348c0580d2ca4e4841fe3143e66c9884","observation_id":"7c5bd1bd-7ed0-443d-aa0f-f7e3f0cd0ad9","resolution":{"observed_at":"2026-08-08T13:05:53.455420Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.459073Z","title":"Spherical image generation from a single image by consid- ering scene symmetry","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.459073Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:e7d416b21f21d62f729fca40e08e19fe250a866c3adcbe0e109d093d34ac6630","observation_id":"564f0edd-8cc5-4083-ae8c-18fa35b6d241","resolution":{"observed_at":"2026-08-08T13:05:53.459073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.463342Z","title":"Zhang, Shaoqing Ren, and Jian Sun","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.463342Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:5eba198539a3565f7bb4fae36ba76b9f507f5a2663a3c2b320c3bf3c171e2336","observation_id":"dfc5015e-9239-43a5-bd66-6a1e8213581d","resolution":{"observed_at":"2026-08-08T13:05:53.463342Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.467246Z","title":"Riecke, and Lillian Yang","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.467246Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:8669bfa28a58dfca3d1231f3c8fb3ad8b8232b39c1259615740b557dd82161eb","observation_id":"a7956e20-73e9-411b-b9ab-51c32d6eaa6b","resolution":{"observed_at":"2026-08-08T13:05:53.467246Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.471227Z","title":"Generative adversarial imitation learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.471227Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:39d0efba410b6ea7ec12ec5ab9c6c5124d361504d848bc1a16327d9ec0c74be1","observation_id":"90b2d4a1-2905-4853-9ddc-4d52cb4da588","resolution":{"observed_at":"2026-08-08T13:05:53.471227Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.474891Z","title":"Deep sky modeling for single image outdoor lighting estimation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.474891Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:1b95d04d722ba207aa92a88487429c5deed35ab02b015a3ef1a3e4c10e4ce4d2","observation_id":"4e78dab4-cd2f-4ed6-b7aa-f6b440454807","resolution":{"observed_at":"2026-08-08T13:05:53.474891Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.478549Z","title":"Deep outdoor illumination estimation.CVPR, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.478549Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:99820e600872c15f9d81292d155db66b5a048aeff4be13abef2febf9c2102eb5","observation_id":"3d1b56f3-3751-4c9d-a524-3c6e5443df72","resolution":{"observed_at":"2026-08-08T13:05:53.478549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.482454Z","title":"Panoramic image reflection removal","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.482454Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:c553e3b90b48f501d1b5745bdcd74338826df378244fb04b4403c82af6a234d4","observation_id":"438506af-0159-451a-bdbb-3ff981c40e7c","resolution":{"observed_at":"2026-08-08T13:05:53.482454Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.486378Z","title":"Par 2 net: End-to-end panoramic image reflection removal.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(10):12192– 12205, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.486378Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:73773623cffaa51e8da29e3ce2f8e6fdd33300394e1d028ce70bc97e8756bed3","observation_id":"6738ee93-d6c2-444a-aa53-3bd09e11b329","resolution":{"observed_at":"2026-08-08T13:05:53.486378Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.490141Z","title":"Image quality metrics: Psnr vs","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.490141Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:6dddd4cf2540a614ab2e86030b3b70db79c046bb5ab1685bb3a17600877d1fc9","observation_id":"51555930-f4b1-46cb-bba4-f2fc8510affc","resolution":{"observed_at":"2026-08-08T13:05:53.490141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.493744Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.493744Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:1bf7d1c7b33620566d4a715821759f211f30e913bcf107bfa013989a4c840353","observation_id":"1b8ccc13-e556-494c-b049-f15c14844da6","resolution":{"observed_at":"2026-08-08T13:05:53.493744Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.497385Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.497385Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:4ed16713fe55795c6cc6afc9ece0f780e9198d0ca1dfe86768988ee55069a4b7","observation_id":"1d01cb07-5f82-405b-a0e8-4eb4747fd21b","resolution":{"observed_at":"2026-08-08T13:05:53.497385Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.501191Z","title":"Omnidirec- tional video quality assessment with causal intervention","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.501191Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:8805d19f14c54f65dbddd88998a0d6099c4fda95f9822c0c81304fe20c809d8d","observation_id":"6913bc69-004d-4ccd-8f60-7a645e68e525","resolution":{"observed_at":"2026-08-08T13:05:53.501191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.505016Z","title":"360vo: Visual odometry using a single 360 camera.2022 International Conference on Robotics and Automation (ICRA), pages 5594–5600, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.505016Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:4d3c921c0087778ee183f17718deb074fc0c307259401273f12fafdfa63e722c","observation_id":"5793260f-a6c2-4349-a381-ca1524eeb33c","resolution":{"observed_at":"2026-08-08T13:05:53.505016Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.508639Z","title":"360loc: A dataset and benchmark for omnidirectional visual localization with cross-device queries","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.508639Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:dfd5ab94055c60de3c5c66891c4d6edbde0413d56f321e63549120157572aff1","observation_id":"9fea59bc-e59c-4465-af89-b7abad68e0a4","resolution":{"observed_at":"2026-08-08T13:05:53.508639Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.512554Z","title":"Surround-view fisheye optics in computer vision and simulation: Survey and challenges.IEEE Transactions on Intelligent Transportation Systems, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.512554Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:a4f6c2d7e9607bb0e166b780bc2986782759994e3d857c31381d873b06ad7783","observation_id":"c62a65d0-1e9d-430d-bf29-ab9268a7cd25","resolution":{"observed_at":"2026-08-08T13:05:53.512554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.516467Z","title":"Panoramic panoptic segmentation: Towards complete sur- rounding understanding via unsupervised contrastive learn- ing","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.516467Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:f936a95be2a6f4e8162f8a98307048fb63961384738b4a92bc9fbe14e48b8b98","observation_id":"892fb43c-25ef-4cf5-8d32-fad10858690b","resolution":{"observed_at":"2026-08-08T13:05:53.516467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.520419Z","title":"Panoramic panoptic segmentation: Insights into surround- ing parsing for mobile agents via unsupervised contrastive learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.520419Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:264395f5206a93dac32d1acbdba8a3364701e4826cc94d7b289eb272b6fddec2","observation_id":"8c24c244-caf9-484e-9fe6-5126afdd29ea","resolution":{"observed_at":"2026-08-08T13:05:53.520419Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T13:05:53.524314Z","title":"Active perception for outdoor localisation with an omnidirectional camera.2020 IEEE/RSJ Inter- national Conference on Intelligent Robots and Systems (IROS), pages 4567–4574, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-08T13:05:53.524314Z"},"links":{"citing_paper":"/paper/2502.10444"},"observation_digest":"sha256:6875f5089f8965d2597a54431afea084b86cdc34d3e6f01634db35c4d25f6dd3","observation_id":"fc8e2fac-43a1-45b2-bc84-457e6aa64916","resolution":{"observed_at":"2026-08-08T13:05:53.524314Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.10444","last_updated":"2025-02-11T08:05:11Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T14:10:10.309456Z","submitted_at":"2025-02-11T08:05:11Z","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":99,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":299},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 100 of 299 outbound references and 2 inbound Pith citation observations for arXiv:2502.10444."}