{"as_of":"2026-08-17T20:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3f3318f9a2f71d0c65814555799669bb28a43046d1120a8a0edd42b597f05f36","coverage":[{"denominator":194,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T10:29:54.583232Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.11093/citation-record","integrity":"/paper/2608.11093/integrity","json":"/paper/2608.11093/citation-record.json","paper":"/paper/2608.11093"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T10:29:54.198803Z","title":"Deep non-rigid structure from motion with missing data,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.198803Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:ae6008eeb5d842f0598a026e1b92ecda6689392b182768c93c5c0ed81cf86932","observation_id":"c42ed459-c1fc-4b19-ae51-2fdf0dac50a1","resolution":{"observed_at":"2026-08-12T10:29:54.198803Z","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":"2026-08-12T10:29:54.203751Z","title":"InLoc: Indoor visual localization with dense matching and view synthesis,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.203751Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:2bcf9cb896ff80e93005f578b4fd0430787fcb248831fbba2f65fe99bdbbaddb","observation_id":"009ab42b-30fb-450f-9fa6-0aa1e847fa2a","resolution":{"observed_at":"2026-08-12T10:29:54.203751Z","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":"2026-08-12T10:29:54.207975Z","title":"Linear RGB-D SLAM for structured environments,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.207975Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:23a47fe52ee868ff520f3ed81e7c54b44706721bbc76fbf939365b64768ac74f","observation_id":"57a00785-7d51-4847-9456-722a4eb41ca5","resolution":{"observed_at":"2026-08-12T10:29:54.207975Z","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":"2026-08-12T10:29:54.212127Z","title":"SuperGlue: Learning feature matching with graph neural networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.212127Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:d4f675c47dce50d874f9af35262e8a9a4ca10bbce279a31a3512d83655f7214b","observation_id":"1e2bcdbe-47b2-4584-a407-a6bafb93e7d0","resolution":{"observed_at":"2026-08-12T10:29:54.212127Z","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":"2026-08-12T10:29:54.216644Z","title":"LoFTR: Detector-free local feature matching with transformers,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.216644Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:f3d4ca11b1b5ae3ce52da93cf7f9d1697e990f11f537eea24e3e869816e2e3e7","observation_id":"3a1981f8-158c-45bf-89b1-22908efd71d7","resolution":{"observed_at":"2026-08-12T10:29:54.216644Z","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":"2026-08-12T10:29:54.221250Z","title":"Jamma: Ultra-lightweight local feature matching with joint mamba,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.221250Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:dbc4ca2dfd623e6afc703329caee0d90c6de5af6111e0b0bd1695eddd8df29ad","observation_id":"1228c833-7a44-4c72-b0d9-589623350e06","resolution":{"observed_at":"2026-08-12T10:29:54.221250Z","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":"2026-08-12T10:29:54.226223Z","title":"MambaGlue: Fast and robust local feature matching with mamba,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.226223Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:86c8bdb72d7d56e5884f1eaa4aaa410ac501b1988351c874089abd2444e0c7d4","observation_id":"13dfc38d-a7e1-4c7f-869c-adf6213dc65a","resolution":{"observed_at":"2026-08-12T10:29:54.226223Z","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":"2026-08-12T10:29:54.230301Z","title":"LightGlue: Local feature matching at light speed,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.230301Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:bf238d98ac1fd34da122647910f653651ca0d9ad97fd15d1067546626b65e58c","observation_id":"7aa018fc-f4fb-4d06-9097-6e9a3b4c2bb6","resolution":{"observed_at":"2026-08-12T10:29:54.230301Z","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":"2026-08-12T10:29:54.234036Z","title":"OmniGlue: Generalizable feature matching with foundation model guidance,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.234036Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:650945e68507de7ae28de5aa3317cfa7f1b55a439e0993928ca6782eed5ca2d9","observation_id":"1028f353-df54-4915-8abf-64e06233961c","resolution":{"observed_at":"2026-08-12T10:29:54.234036Z","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":"2026-08-12T10:29:54.237713Z","title":"Roma: Robust dense feature matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.237713Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:c21114832a168b193066bc77918b15ef98836ec0de355f2b02e90e1ae2867321","observation_id":"2e8ad8f9-fe33-4caf-b602-7ae7f63605f3","resolution":{"observed_at":"2026-08-12T10:29:54.237713Z","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":"2026-08-12T10:29:54.242092Z","title":"Grounding image matching in 3D with MASt3R,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.242092Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:b2a67ca9be406a264f2e17eb657e0f3f35936e878f880f8ac92544b45e541e98","observation_id":"45061f44-5862-4bd7-996d-6a3cc113d9d8","resolution":{"observed_at":"2026-08-12T10:29:54.242092Z","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":"2026-08-12T10:29:54.246159Z","title":"VGGT: Visual geometry grounded transformer,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.246159Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:09cd9d3e3cf34a157d1a3499c045e0dbb2688e8a96e9efec3c9a01627ac5cab9","observation_id":"91c1235c-be19-4848-962d-81da52add4be","resolution":{"observed_at":"2026-08-12T10:29:54.246159Z","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":"2026-08-12T10:29:54.249786Z","title":"Image matching from handcrafted to deep features: A survey,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.249786Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:fb039d4cb4993651e7994731f0f184338b9879ed38a10cb063c7a685951c35f2","observation_id":"030f509b-72d9-48d6-a566-d91d753c1be2","resolution":{"observed_at":"2026-08-12T10:29:54.249786Z","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":"2026-08-12T10:29:54.253502Z","title":"A survey of feature matching methods,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.253502Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:3689dbcc1d276f4ac08ba108c8ece185ce66d2bb4c49abbcb80fa3882cf8357f","observation_id":"db37cb3d-b444-4071-894d-dbf16f79638a","resolution":{"observed_at":"2026-08-12T10:29:54.253502Z","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":"2026-08-12T10:29:54.257005Z","title":"A review of multimodal image matching: Methods and applications,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.257005Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:28513071b3fe3270dd01f126dab44b1e30474586d6d698afc52a0fc58070cbb5","observation_id":"220f5a4c-358e-4e84-be1b-d5c560800330","resolution":{"observed_at":"2026-08-12T10:29:54.257005Z","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":"2026-08-12T10:29:54.260611Z","title":"A combined corner and edge detector,","venue":null,"work_id":null,"year":1988},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.260611Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:c2486c7d9ba8691d0781e572e56db74be0bef282a277f18119b83c47cc140a63","observation_id":"a9688bf8-5f9a-489b-96fd-1eb12507c55f","resolution":{"observed_at":"2026-08-12T10:29:54.260611Z","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":"2026-08-12T10:29:54.265077Z","title":"Distinctive image features from scale-invariant key- points,","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.265077Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:24f2060261d3b5b19d4706daf9e80151ce2ab990b5ed3a1c110c56c524777cc1","observation_id":"50bd8727-55bc-436f-90cd-7af9e5e7a524","resolution":{"observed_at":"2026-08-12T10:29:54.265077Z","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":"2026-08-12T10:29:54.270023Z","title":"SURF: Speeded up robust features,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.270023Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:662bcb365f77ce66458eaaabccad383a54da50d5bcbe7afbd93808dbf3a0fda2","observation_id":"7b8c09db-6faa-4b08-935c-31d62213a726","resolution":{"observed_at":"2026-08-12T10:29:54.270023Z","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":"2026-08-12T10:29:54.274345Z","title":"Robust wide-baseline stereo from maximally stable extremal regions,","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.274345Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:6e06ddf0b170aec63c91bab483ee0245251c078b3eda2f687ba3579dbb7b8031","observation_id":"b8776477-de37-4175-85d0-5a5159281b76","resolution":{"observed_at":"2026-08-12T10:29:54.274345Z","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":"2026-08-12T10:29:54.278296Z","title":"Machine learning for high-speed corner detection,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.278296Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:b3ce1cde938eb9cdf87e20a3e76412b39e76594d71cb81ce0b5655301a0ca717","observation_id":"164d7db5-0244-4011-9849-cf948d8dff5f","resolution":{"observed_at":"2026-08-12T10:29:54.278296Z","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":"2026-08-12T10:29:54.282303Z","title":"Adaptive and generic corner detection based on the accelerated segment test,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.282303Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:0b5de309f2cfdf8e6a22233e7c2c6edeacc9d8d8e63689b0f74bfc3b552cca71","observation_id":"57f18509-8b21-45c6-b3d9-d2a19978031d","resolution":{"observed_at":"2026-08-12T10:29:54.282303Z","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":"2026-08-12T10:29:54.286395Z","title":"KAZE features,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.286395Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:769e0af13831698253fb7abfac95b8bc0dcda1debf5d2bdc738f707f40cf49b1","observation_id":"1faa76a9-1a23-41db-8bb4-3bab77ae407a","resolution":{"observed_at":"2026-08-12T10:29:54.286395Z","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":"2026-08-12T10:29:54.290863Z","title":"Fast explicit diffusion for accelerated features in nonlinear scale spaces,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.290863Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:27545abf04d4808cfc863037728c60ac1115c43f8ffa8cccc83e0c242360b1a2","observation_id":"fb1a6afd-04d1-4b97-8ec0-bf3706d3cf99","resolution":{"observed_at":"2026-08-12T10:29:54.290863Z","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":"2026-08-12T10:29:54.295315Z","title":"BRISK: Binary robust invariant scalable keypoints,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.295315Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:22b38fe44aa3b7799406dfd560726e1eb653076e58932640370121b4447e9994","observation_id":"6b786e08-8590-4019-a17f-cd4641543b86","resolution":{"observed_at":"2026-08-12T10:29:54.295315Z","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":"2026-08-12T10:29:54.299530Z","title":"LIFT: Learned invariant feature transform,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.299530Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:3f13bb67ba544a7a35d3bbf32ef7df8e6520264b0dc3fb345d65da4aa7652890","observation_id":"fe3c829f-70dc-43b6-9747-31885cddaeb0","resolution":{"observed_at":"2026-08-12T10:29:54.299530Z","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":"2026-08-12T10:29:54.304134Z","title":"TILDE: A temporally invariant learned detector,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.304134Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:bc9b552708863164b448cea9d55e1a41dc2243d9acffe0423ee643a99e8445a4","observation_id":"0cc13644-329b-48cd-9194-3adc958bbada","resolution":{"observed_at":"2026-08-12T10:29:54.304134Z","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":"2026-08-12T10:29:54.308537Z","title":"SuperPoint: Self- supervised interest point detection and description,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.308537Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:3ea034385cd92df10ed65759100d0fd80888b8a812b9c510cba3a40abf7344c7","observation_id":"8516ef24-9664-40d6-862a-1a02cee8339c","resolution":{"observed_at":"2026-08-12T10:29:54.308537Z","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":"2026-08-12T10:29:54.312699Z","title":"D2-Net: A trainable CNN for joint description and detection of local features,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.312699Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:04d369e298411b4141a65505f11e6d997e7af0a4879859c44f1209f619673366","observation_id":"bd861afc-b576-439b-befe-c32c216f7912","resolution":{"observed_at":"2026-08-12T10:29:54.312699Z","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":"2026-08-12T10:29:54.316938Z","title":"R2D2: Reliable and repeatable detector and descriptor,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.316938Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:5a18027603f7cc31ed260fc8503b091490c7314405e0bfcc959568c4cda4489c","observation_id":"25e9d22d-69ac-4716-9953-a08de71d5264","resolution":{"observed_at":"2026-08-12T10:29:54.316938Z","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":"2026-08-12T10:29:54.320242Z","title":"Key.Net: Keypoint detection by handcrafted and learned CNN filters,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.320242Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:f7c6b8a10f0c232c745504739eacce6839c81a6d2325a570cac306f823a50069","observation_id":"8aef27b8-85d2-4a6a-b0cb-78302be304e2","resolution":{"observed_at":"2026-08-12T10:29:54.320242Z","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":"2026-08-12T10:29:54.323688Z","title":"Key.Net: Keypoint detection by handcrafted and learned CNN filters revisited,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.323688Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:783772d28ce0cfefd727316d2a5b21dc8128ef506eee26d1b328a5820c00bd43","observation_id":"d2549af7-6286-419b-9eb5-8be281575c99","resolution":{"observed_at":"2026-08-12T10:29:54.323688Z","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":"2026-08-12T10:29:54.327353Z","title":"ALIKE: Accurate and lightweight keypoint detection and descriptor extraction,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.327353Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:d932c97fd8036aa3b981bc71d07d598bef660f232197f36f0315c05b1ed7a524","observation_id":"caab876a-cfc5-4083-af33-1c60545128c4","resolution":{"observed_at":"2026-08-12T10:29:54.327353Z","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":"2026-08-12T10:29:54.331190Z","title":"Quad- Networks: Unsupervised learning to rank for interest point detection,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.331190Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:2dcca49d65f193b06b63a4583bdf7d34090929320d07738f841f879b7e794c4a","observation_id":"86549d0d-cdc3-43f1-9aa8-b46a2d0d5b85","resolution":{"observed_at":"2026-08-12T10:29:54.331190Z","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":"2026-08-12T10:29:54.335723Z","title":"Disk: Learning local fea- tures with policy gradient,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.335723Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:c6733f140eb9d666e35a9615d39f39143b042f4533affa65d5b8b513137f17b8","observation_id":"564c32f7-9f07-453c-85de-b08a14c9649d","resolution":{"observed_at":"2026-08-12T10:29:54.335723Z","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":"2026-08-12T10:29:54.339774Z","title":"Dedode v2: Analyzing and improving the dedode keypoint detector,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.339774Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:4f4b9545559271f443d3074f81a18b668a8b9867e6442ef8a46ee907e488e57f","observation_id":"a30033f3-7854-4bb1-bf89-1ba27ef1f504","resolution":{"observed_at":"2026-08-12T10:29:54.339774Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.07347","last_updated":"2025-03-11T02:23:20Z","snapshot_observed_at":"2026-08-16T12:51:30.721496Z","submitted_at":"2025-03-10T14:02:30Z","title":"DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.07347","snapshot_observed_at":"2026-08-12T10:29:54.344055Z","title":"DaD: Distilled reinforcement learning for diverse keypoint detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.344055Z"},"links":{"cited_paper":"/paper/2503.07347","citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:8f8b4e9cf31cf74762babe41633d072f65f2df6d619ef9d0173c73c866bd51b3","observation_id":"5e4442ff-e476-4435-a677-e9c452c0068b","resolution":{"observed_at":"2026-08-12T10:29:54.344055Z","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":"2026-08-12T10:29:54.348323Z","title":"PCA-SIFT: a more distinctive representation for local image descriptors,","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.348323Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:0a9212061750a2b90c23ab01b0ac02dc2049ce15d4416b17396e3314cc862e7d","observation_id":"073b3d11-8635-4739-a17b-ad066e88e57d","resolution":{"observed_at":"2026-08-12T10:29:54.348323Z","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":"2026-08-12T10:29:54.351698Z","title":"A performance evaluation of local descriptors,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.351698Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:ff390b8404677f3d888f5b29b114fde390e6e186e2c1fd3878b2ffcb235b0569","observation_id":"c7b6f2c1-5a96-4527-b10f-618cc532a69c","resolution":{"observed_at":"2026-08-12T10:29:54.351698Z","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":"2026-08-12T10:29:54.355332Z","title":"BRIEF: Binary robust independent elementary features,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.355332Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:6c2eb284c29f0bce2dff2fcef17b7af7180e07de84fd19f5225503cff53e5305","observation_id":"dcb8260e-dec5-4545-8a48-2ed0736a9f1f","resolution":{"observed_at":"2026-08-12T10:29:54.355332Z","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":"2026-08-12T10:29:54.359078Z","title":"FREAK: Fast retina key- point,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.359078Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:2057428698023ee43c75a6b05391521f4d86fb7b8809e66780398adb3186f69d","observation_id":"020054b6-dca8-4954-9dd1-b89e532b4aaa","resolution":{"observed_at":"2026-08-12T10:29:54.359078Z","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":"2026-08-12T10:29:54.362770Z","title":"Local intensity order pattern for feature description,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.362770Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:369591b44b5f6e2e1ec4756ebcfe2bdc0e14c0af070724f484492064e97cc982","observation_id":"32ba067b-5d8d-4010-b48d-0e5e76d8199e","resolution":{"observed_at":"2026-08-12T10:29:54.362770Z","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":"2026-08-12T10:29:54.366649Z","title":"Rethinking the sGLOH descriptor,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.366649Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:78123cfd49d8b39b70161c99f3e42ebc5c6afb6c92e64ff2acabf7ec93dbcc79","observation_id":"4bb60a09-558c-4f04-a8bb-4a6e15679ba8","resolution":{"observed_at":"2026-08-12T10:29:54.366649Z","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":"2026-08-12T10:29:54.370020Z","title":"Discriminative learning of deep convolutional feature point descriptors,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.370020Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:59f6ffc898a84f0c1377a3a600aa75ebbf3c9900adf44c9663d38023b1e0559d","observation_id":"31cdc2e2-4404-43d1-9664-b23341ebdc1e","resolution":{"observed_at":"2026-08-12T10:29:54.370020Z","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":"2026-08-12T10:29:54.373574Z","title":"L2-Net: Deep learning of discrimina- tive patch descriptor in Euclidean space,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.373574Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:5f1863320b0861b922e005ef2be5d49a1267b8f8f216365a9abccc6645573f55","observation_id":"0488c566-e872-4596-96c8-78173def4660","resolution":{"observed_at":"2026-08-12T10:29:54.373574Z","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":"2026-08-12T10:29:54.376924Z","title":"Working hard to know your neighbor’s margins: local descriptor learning loss,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.376924Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:7dd5e8a48550a445e76f989f5252231de3c3dce6f6bc004b7223caf6135dc35b","observation_id":"7ea363ec-d210-4bf8-9f6d-1b252614b670","resolution":{"observed_at":"2026-08-12T10:29:54.376924Z","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":"2026-08-12T10:29:54.380327Z","title":"Learning local image descriptors with deep siamese and triplet convolutional networks by minimizing global loss functions,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.380327Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:02359087d873fc5ea65c67431d6427aa8f45c31d43c54b0cc3816a82f549fdb6","observation_id":"4fdaa36a-ca2c-4179-9c69-8ca9ac86ffee","resolution":{"observed_at":"2026-08-12T10:29:54.380327Z","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":"2026-08-12T10:29:54.383743Z","title":"GeoDesc: Learning local descriptors by integrating geometry constraints,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.383743Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:521915285d48c354304095a9d7974644efc93145846863f72462b734c68da56c","observation_id":"e4e68600-37c7-4559-b403-e5cfed3dc34d","resolution":{"observed_at":"2026-08-12T10:29:54.383743Z","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":"2026-08-12T10:29:54.388090Z","title":"Local descriptors optimized for average precision,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.388090Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:70cef165d3b7e24d300fa7fb8cfd429ae9fd37ec9a09df50f9cad8826afd25b9","observation_id":"c2edf3d3-99ad-4ec9-9fee-55e3cd8a25bc","resolution":{"observed_at":"2026-08-12T10:29:54.388090Z","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":"2026-08-12T10:29:54.391709Z","title":"ContextDesc: Local descriptor augmentation with cross- modality context,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.391709Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:8546f9fa0d976edb7228e14250166969595605b710f94a24382893261ca6fb8f","observation_id":"9dcbd421-1cdc-44d9-8361-12016fee6040","resolution":{"observed_at":"2026-08-12T10:29:54.391709Z","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":"2026-08-12T10:29:54.395519Z","title":"HyNet: learning local descriptor with hybrid similarity measure and triplet loss,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.395519Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:89495097e07d6794f83f3cb344a6a30e131527323b25000e9bf8de00a208b52e","observation_id":"c4dbc255-9745-4294-9b00-948b7100f85e","resolution":{"observed_at":"2026-08-12T10:29:54.395519Z","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":"2026-08-12T10:29:54.399001Z","title":"SOSNet: Second order similarity regularization for local descriptor learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.399001Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:660be7455120af9a63992114c3a74554570358aced6365b96f0981671b081adb","observation_id":"aacbf1e4-8375-4f60-b564-c7713653085d","resolution":{"observed_at":"2026-08-12T10:29:54.399001Z","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":"2026-08-12T10:29:54.402332Z","title":"Zippypoint: Fast interest point detection, description, and matching through mixed precision discretization,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.402332Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:489f7094a95feb31bf6d9c9cd8c55808a582747726415cb7b82e5d9abb991675","observation_id":"9ffa5e58-863d-4fd7-9c7c-cf73717fd05d","resolution":{"observed_at":"2026-08-12T10:29:54.402332Z","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":"2026-08-12T10:29:54.406376Z","title":"Xfeat: Accelerated features for lightweight image matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.406376Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:b82a06502525a4ec58e5a08cd6e652a7e3da7fccb0e81141577a09f7748a1dc5","observation_id":"81087426-8822-40fa-bbf1-87f327ff44b1","resolution":{"observed_at":"2026-08-12T10:29:54.406376Z","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":"2026-08-12T10:29:54.410316Z","title":"NCTR: Neighborhood consensus transformer for feature matching,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.410316Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:0804c95566710737af484eeced5afe48186fdebb8dd68f5040dc2de7fee6f657","observation_id":"47f614cd-169f-4722-83b7-cb3fd27edf64","resolution":{"observed_at":"2026-08-12T10:29:54.410316Z","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":"2026-08-12T10:29:54.413691Z","title":"DNC-Net: Dual-neighbourhood consensus net- work for feature matching,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.413691Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:d4a1669941c5122ec1b1a332aaa3a030032e6ec7be6b48f71be5b838940d6f29","observation_id":"6427698a-d457-4ad7-8a62-df02c24154fc","resolution":{"observed_at":"2026-08-12T10:29:54.413691Z","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":"2026-08-12T10:29:54.417181Z","title":"IMP: Iterative matching and pose estimation with adaptive pooling,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.417181Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:dd5dd0c42de0aad543427192562f18db4dba7fdeaeececcf8c285a242270ab45","observation_id":"79f27bae-0c6c-40c2-acac-165156940bd5","resolution":{"observed_at":"2026-08-12T10:29:54.417181Z","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":"2026-08-12T10:29:54.420658Z","title":"Scene-aware feature matching,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.420658Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:4527c2035b89fdb7697c6869852ec79b4963d57ce1f5efe9e20d5d7000e3e8b6","observation_id":"807e4619-4b43-4995-bd55-9ac3ffb3e58f","resolution":{"observed_at":"2026-08-12T10:29:54.420658Z","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":"2026-08-12T10:29:54.425160Z","title":"S2H- GNN: Learning soft to hard feature matching with sparsified graph neural network,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.425160Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:d52aa22b278e6636edd201746fbe919a58a725c4a64067340254b559a4592f98","observation_id":"bb3e1875-7637-4bb3-8a56-2901d79368d2","resolution":{"observed_at":"2026-08-12T10:29:54.425160Z","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":"2026-08-12T10:29:54.428463Z","title":"HTMatch: An efficient hybrid transformer based graph neural network for local feature match- ing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.428463Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:f8a920e705579e35425a9c8c17ce4a708e91ee4e39f3abc103791d3f3a1f46e4","observation_id":"a5abb442-63df-45e8-8426-0f007be69189","resolution":{"observed_at":"2026-08-12T10:29:54.428463Z","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":"2026-08-12T10:29:54.432076Z","title":"DiffGlue: Diffusion-aided image feature match- ing,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.432076Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:183fce378a86e2ac8ed5031b875c747b5e15087d42a53f2a839f9b01f552299a","observation_id":"3abca9ca-cfa1-464f-98d9-a0fc742fa914","resolution":{"observed_at":"2026-08-12T10:29:54.432076Z","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":"2026-08-12T10:29:54.435655Z","title":"ResMatch: Residual attention learning for feature matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.435655Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:bad73d68c600dce1957c79f23a743721ba299e62cfa3e5344164fd7ec24412c3","observation_id":"00574e76-f51d-4c30-b959-50f5071f87e5","resolution":{"observed_at":"2026-08-12T10:29:54.435655Z","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":"2026-08-12T10:29:54.439663Z","title":"Matching while perceiving: Enhance image feature matching with applicable semantic amalgama- tion,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.439663Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:6aeb9ecf8b4bbbaa2387850a4105e25316e27569fce15f0357339e731a538c35","observation_id":"0f35054d-3a5d-438e-81cb-c3d9a5d0b99c","resolution":{"observed_at":"2026-08-12T10:29:54.439663Z","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":"2026-08-12T10:29:54.442884Z","title":"SemMatcher: Semantic- aware feature matching with neighborhood consensus,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.442884Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:92fa8674d4e689a5b9e0106000901e16993cb5ca19bd108cfd8391f3147767bd","observation_id":"e8ae62c5-d23b-4800-b484-773ddd8b6637","resolution":{"observed_at":"2026-08-12T10:29:54.442884Z","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":"2026-08-12T10:29:54.446140Z","title":"CoMatcher: Multi-view collaborative feature matching,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.446140Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:5181cdaaf9f9c33b67103e58c9e72e05dd8dfc51cc826dd01039870b84c06481","observation_id":"7a6cdd51-3a6a-4c3b-a2d2-4e51f55d6518","resolution":{"observed_at":"2026-08-12T10:29:54.446140Z","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":"2026-08-12T10:29:54.449686Z","title":"AAPMatcher: Adaptive attention pruning matcher for accurate local feature matching,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.449686Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:41a8b65fdd0f30ddc5b391a3f448e776e0def09cafd7eb054ef12d2f67ad90b4","observation_id":"07a1a1d2-8e5f-4247-9e0f-21c78eda1c49","resolution":{"observed_at":"2026-08-12T10:29:54.449686Z","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":"2026-08-12T10:29:54.454542Z","title":"Learning to match features with seeded graph matching network,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.454542Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:8b3f5ffcbb0bb396cae16638a33eaa53cefcbe038a9a10fef1c95482489a8622","observation_id":"8a8c43b9-172f-44ea-b626-820a7dadf6ae","resolution":{"observed_at":"2026-08-12T10:29:54.454542Z","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":"2026-08-12T10:29:54.458051Z","title":"Improving sparse graph attention for feature matching by informative keypoints exploration,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.458051Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:676dbb19658297f8f45624cd630240dd343c873c360b9e006dbaf08e63fe5c3c","observation_id":"c39bbbac-a4ea-492e-bfb4-2fc3ff321cd6","resolution":{"observed_at":"2026-08-12T10:29:54.458051Z","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":"2026-08-12T10:29:54.461562Z","title":"ClusterGNN: Cluster-based coarse-to-fine graph neural network for efficient feature matching,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.461562Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:59fbd19ea124acdacaa8f84faf786759965874e83e1f636a85f1030c253bb39c","observation_id":"fda0cdd9-7cce-466d-af26-79d140472bc8","resolution":{"observed_at":"2026-08-12T10:29:54.461562Z","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":"2026-08-12T10:29:54.465184Z","title":"Learning to match features with discriminative sparse graph neural network,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.465184Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:86192b6d5efa952aa022b2040df6c05fe67711ebb203fd020bd17bd327e5d737","observation_id":"611e3d88-b278-4a38-9914-88271e0042f9","resolution":{"observed_at":"2026-08-12T10:29:54.465184Z","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":"2026-08-12T10:29:54.468596Z","title":"ParaFormer: Parallel attention transformer for efficient feature matching,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.468596Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:fdd5964414d093207c5cbb5536c7aa949600fed1cc70a6b30e9114985d460c7b","observation_id":"adf08b25-89f7-4379-9bdc-985ceeca1e2e","resolution":{"observed_at":"2026-08-12T10:29:54.468596Z","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":"2026-08-12T10:29:54.472058Z","title":"AMatFormer: Efficient feature matching via anchor matching transformer,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.472058Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:d731c04f0ab503409c914a352247dc52fe8cc7e3881ecd7b3bcb15b40588a62c","observation_id":"f04b8cbf-d546-46f1-a113-aaf20081fbc2","resolution":{"observed_at":"2026-08-12T10:29:54.472058Z","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":"2026-08-12T10:29:54.475478Z","title":"LightSGM: Local feature matching with lightweight seeded,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.475478Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:cd57bc45d5d269166d800a233ebdd250d7c8bd8f9949021a0f3cca9a319480b6","observation_id":"618c75b3-5774-4620-9305-ddf64ebec217","resolution":{"observed_at":"2026-08-12T10:29:54.475478Z","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":"2026-08-12T10:29:54.478942Z","title":"FilterGNN: Image feature matching with cascaded outlier filters and linear attention,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.478942Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:7f74999e99e4106c6abcb27b3d6787acfa75b711eafbdc92c52077dfdb9296aa","observation_id":"dcd8494f-df14-45b3-bada-f6713c1ccb6c","resolution":{"observed_at":"2026-08-12T10:29:54.478942Z","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":"2026-08-12T10:29:54.483359Z","title":"Learning feature matching via matchable keypoint- assisted graph neural network,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.483359Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:2876a217e9ca3ee9248a802f74ab39f55f4fab7fdb53fc3e278902c2519d75d0","observation_id":"800f5214-4e5e-4ade-a051-5bd28b200767","resolution":{"observed_at":"2026-08-12T10:29:54.483359Z","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":"2026-08-12T10:29:54.486759Z","title":"Ada- Matcher: A deep detector-based local feature matcher with adaptive weight sharing,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.486759Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:9702e0a180a0c0b88cc3fa26a2a5699e09a4a7d1ea2cc86405328212c301856b","observation_id":"fa72786e-f763-4b69-8055-cb701647adc2","resolution":{"observed_at":"2026-08-12T10:29:54.486759Z","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":"2026-08-12T10:29:54.490050Z","title":"LFM-3D: Learnable feature matching across wide baselines using 3D signals,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.490050Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:a0f4eba06997961ac5517573a71297a3d105861d391b6c91f306ae5cfb11aa4a","observation_id":"8cb32076-1366-401f-bdca-93cb63fd53ab","resolution":{"observed_at":"2026-08-12T10:29:54.490050Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.16185","last_updated":"2025-03-20T14:36:16Z","snapshot_observed_at":"2026-08-16T12:48:15.882384Z","submitted_at":"2025-03-20T14:36:16Z","title":"MapGlue: Multimodal Remote Sensing Image Matching","version":1},"cited_work":{"arxiv_id":"2503.16185","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.16185","snapshot_observed_at":"2026-08-12T10:29:55.359026Z","title":"MapGlue: Multimodal Remote Sensing Image Matching","venue":"cs.CV","work_id":"1d36d64c-b4bb-4e1c-b88d-2b9c79c4aea0","year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.493427Z"},"links":{"cited_paper":"/paper/2503.16185","citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:545b77a1222c475426690fe83164eec1650f2b9dcd96541b998fdc9391bad806","observation_id":"503feab4-33b6-4891-8098-42710ca76e0f","resolution":{"observed_at":"2026-08-12T10:29:55.363992Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-12T10:29:54.497383Z","title":"Patch2Pix: Epipolar-guided pixel-level correspondences,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.497383Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:8c17249141c08b3d26dbda11b2902b661a178898dd019bb5d3a8027277589b1c","observation_id":"56ffae71-53a8-41da-a718-19c2e56fd557","resolution":{"observed_at":"2026-08-12T10:29:54.497383Z","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":"2026-08-12T10:29:54.500916Z","title":"Match- Former: Interleaving attention in transformers for feature matching,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.500916Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:f74ed101c085cede5c0c59c3c3ddc1a17ccc860b31a93268ba84fd8fa5f3f4f1","observation_id":"269e1361-8e97-4a5e-b497-6f631177c3f0","resolution":{"observed_at":"2026-08-12T10:29:54.500916Z","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":"2026-08-12T10:29:54.504595Z","title":"ASpanFormer: Detector-free image matching with adaptive span transformer,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.504595Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:8bba299b89aaff6793b39bad1094fc296c01e6bb26ebeff30f09dd767f974f78","observation_id":"e8919703-6429-4f47-a666-4dbbb5a9d723","resolution":{"observed_at":"2026-08-12T10:29:54.504595Z","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":"2026-08-12T10:29:54.508000Z","title":"3DG-STFM: 3D geometric guided student-teacher feature matching,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.508000Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:101c93b0574f17bb144d5fcdc0ecfa30c6f462eecf5f86c03508a54e7a86eb63","observation_id":"98aedd7c-941b-4e3a-a2b5-a97ebdc8f07c","resolution":{"observed_at":"2026-08-12T10:29:54.508000Z","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":"2026-08-12T10:29:54.511696Z","title":"MSFormer: Multi-scale trans- former with neighborhood consensus for feature matching,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.511696Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:613e54ec0aac09eae0da931c45108bff194ab2b3a0ac5191a421467587cc3ec0","observation_id":"58d3fea5-4506-43f8-a3ac-f3861b867512","resolution":{"observed_at":"2026-08-12T10:29:54.511696Z","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":"2026-08-12T10:29:54.515734Z","title":"TopicFM: Robust and interpretable topic-assisted feature matching,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.515734Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:c75735f24b85aad81cfc94ada17ca5494585730e975d2c2824ef17323b7a5195","observation_id":"4c93144c-c2f9-4d70-b16c-8b51b765ec1c","resolution":{"observed_at":"2026-08-12T10:29:54.515734Z","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":"2026-08-12T10:29:54.519844Z","title":"TopicFM+: Boosting accuracy and efficiency of topic-assisted feature matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.519844Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:ab407c790e8c6b39420ff37d39dc8a5620efbda0e2ad13396f67b4c2d7bfe061","observation_id":"5e3884d4-e12e-4ae6-b375-8e5bdcb578dd","resolution":{"observed_at":"2026-08-12T10:29:54.519844Z","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":"2026-08-12T10:29:54.524381Z","title":"Adaptive spot- guided transformer for consistent local feature matching,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.524381Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:d2f74e5aaa0867992de5f2f748a9b68a7bf22e63c97aae00de96c449be0ac382","observation_id":"b10a1388-e22a-4f1b-9c21-b9637bbebb40","resolution":{"observed_at":"2026-08-12T10:29:54.524381Z","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":"2026-08-12T10:29:54.528165Z","title":"Structured epipolar matcher for local feature matching,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.528165Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:bfd01b733696787c3e65f12c4184ea69c9f8b397036c316dbd14d9d2fdabe542","observation_id":"9c2653d8-67bf-481e-b799-d3c069c96c32","resolution":{"observed_at":"2026-08-12T10:29:54.528165Z","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":"2026-08-12T10:29:54.532630Z","title":"Affine-based deformable attention and selective fusion for semi-dense matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.532630Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:28d21d8228eece984ecb8f014199cca137f40209a2dc0e52cb1c987555c6fc5d","observation_id":"d1931f02-ffa5-470b-ae79-bb75297caf11","resolution":{"observed_at":"2026-08-12T10:29:54.532630Z","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":"2026-08-12T10:29:54.536788Z","title":"Beyond global cues: Unveiling the power of fine details in image matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.536788Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:cd3195ce9485312b2b8b17e879212d87af6ee6ec14bfdb8f2813a853bf3f8092","observation_id":"8590e45f-7f3d-484a-9eec-ef0fea9b0d6e","resolution":{"observed_at":"2026-08-12T10:29:54.536788Z","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":"2026-08-12T10:29:54.540445Z","title":"PRISM: Progressive dependency maximization for scale-invariant image matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.540445Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:b31962c459efa885e3d61c82dd394222e44146b9e21e3dd100d2f0e61097e73c","observation_id":"6296731e-dd54-45d7-a9de-76469415c6de","resolution":{"observed_at":"2026-08-12T10:29:54.540445Z","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":"2026-08-12T10:29:54.544393Z","title":"ContextMatcher: Detector-free feature matching with cross-modality context,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.544393Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:098992665c6620189609ccc6907fc1a463369fddbff3329ec7d19b3a1456621f","observation_id":"e752dd0c-ee79-4840-ae11-241957b2830d","resolution":{"observed_at":"2026-08-12T10:29:54.544393Z","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":"2026-08-12T10:29:54.548097Z","title":"DeepMatcher: A deep transformer-based network for robust and accurate local feature matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.548097Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:a080398f4b55c906ad775cdd4304f55be59e49f9c18277b82304b2ec100a4f38","observation_id":"4048810e-9e4a-49b5-b207-0edd491f8582","resolution":{"observed_at":"2026-08-12T10:29:54.548097Z","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":"2026-08-12T10:29:54.551745Z","title":"FMAP: Learning robust and accurate local feature matching with anchor points,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.551745Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:72fedecb37d60f8e796c117c74c705795bdf3289ac258855c39cf291470b7597","observation_id":"879b567f-2bf0-4296-b634-1b17c377652d","resolution":{"observed_at":"2026-08-12T10:29:54.551745Z","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":"2026-08-12T10:29:54.555356Z","title":"OAMatcher: An overlapping areas- based network with label credibility for robust and accurate feature matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.555356Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:618486d02315756d5f5a75d6bca657ce5ad329bcb714af729943fcfa443c6c7e","observation_id":"15db0028-95cc-4eca-8e1f-717d9fa0475b","resolution":{"observed_at":"2026-08-12T10:29:54.555356Z","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":"2026-08-12T10:29:54.558968Z","title":"DSAP: Dynamic sparse attention perception matcher for accurate local feature matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.558968Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:229a1b7d5110ab1e889d9edc2562f182779f0d642c81da924e95525b26b08b51","observation_id":"41df6b0e-73cb-4967-b61a-096a1e27df45","resolution":{"observed_at":"2026-08-12T10:29:54.558968Z","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":"2026-08-12T10:29:54.563006Z","title":"CorMatcher: A corners-guided graph neural network for local feature matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.563006Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:603e41839b52d8eb8ee7baa93c2fc1f8d735f1ac52f20329b1cd314a32f4ce75","observation_id":"c8078b41-05fc-4227-8ad5-00bc4fb35e9d","resolution":{"observed_at":"2026-08-12T10:29:54.563006Z","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":"2026-08-12T10:29:54.566893Z","title":"MR-Matcher: a multirouting transformer-based network for accurate local feature matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.566893Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:902b3ea758aecd5c2752b0e6bb66a6118614e9d9c80e170e2e88f9d29adbd1bc","observation_id":"141d889e-0312-44cb-a090-94238e62a7bc","resolution":{"observed_at":"2026-08-12T10:29:54.566893Z","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":"2026-08-12T10:29:54.570853Z","title":"FMRT: Learning accurate feature matching with reconciliatory transformer,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.570853Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:09287d07b57a5fb25cd2d49c57ad344aa011865adef10108beb97fd892b8091c","observation_id":"6b1cfd45-d3ad-4829-b765-2b2a0b8f3028","resolution":{"observed_at":"2026-08-12T10:29:54.570853Z","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":"2026-08-12T10:29:54.575207Z","title":"WinMRSI: Feature matching with window attention for multi-modal remote sensing image,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.575207Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:4ba2df700d6e65b8520af7948d4aae4bf69b57d211ca850b73da9432494f3f34","observation_id":"d74c2b1a-6850-4ed6-88ec-14c44e0d2ed9","resolution":{"observed_at":"2026-08-12T10:29:54.575207Z","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":"2026-08-12T10:29:54.579197Z","title":"LGFCTR: Local and global feature convolu- tional transformer for image matching,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.579197Z"},"links":{"citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:5819585b538f94fae39b3ab4ec5ec9e91db21ad7f86fefacb732470433ca8496","observation_id":"db11bbe4-bbc6-46d5-9fc3-fde3511f4bab","resolution":{"observed_at":"2026-08-12T10:29:54.579197Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.23925","last_updated":"2025-03-31T10:17:01Z","snapshot_observed_at":"2026-08-16T12:45:24.605283Z","submitted_at":"2025-03-31T10:17:01Z","title":"CoMatch: Dynamic Covisibility-Aware Transformer for Bilateral Subpixel-Level Semi-Dense Image Matching","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.23925","snapshot_observed_at":"2026-08-12T10:29:54.583232Z","title":"CoMatch: Dynamic covisibility-aware transformer for bilateral subpixel-level semi-dense image matching,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-12T10:29:54.583232Z"},"links":{"cited_paper":"/paper/2503.23925","citing_paper":"/paper/2608.11093"},"observation_digest":"sha256:e35587213cc50de50ee9a1f1807077daa432371e8f55eabb8749b3e57999f8a1","observation_id":"5dc4dcc3-5f43-493a-bb80-0cea3c01ff58","resolution":{"observed_at":"2026-08-12T10:29:54.583232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.11093","last_updated":"2026-08-11T16:00:40Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T01:04:53.815465Z","submitted_at":"2026-08-11T16:00:40Z","title":"Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives"},"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":194},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 100 of 194 outbound references and 0 inbound Pith citation observations for arXiv:2608.11093."}