{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LQBUDQLBGE4SHX3UPW7PE2IMNR","short_pith_number":"pith:LQBUDQLB","schema_version":"1.0","canonical_sha256":"5c0341c161313923df747dbef2690c6c4f17fcee250f65333bbe5b2f6255c57d","source":{"kind":"arxiv","id":"2407.11730","version":2},"attestation_state":"computed","paper":{"title":"Monocular Occupancy Prediction for Scalable Indoor Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxiao Yu, Yuntao Chen, Yuqi Wang, Zhaoxiang Zhang","submitted_at":"2024-07-16T13:50:40Z","abstract_excerpt":"Camera-based 3D occupancy prediction has recently garnered increasing attention in outdoor driving scenes. However, research in indoor scenes remains relatively unexplored. The core differences in indoor scenes lie in the complexity of scene scale and the variance in object size. In this paper, we propose a novel method, named ISO, for predicting indoor scene occupancy using monocular images. ISO harnesses the advantages of a pretrained depth model to achieve accurate depth predictions. Furthermore, we introduce the Dual Feature Line of Sight Projection (D-FLoSP) module within ISO, which enhan"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.11730","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T13:50:40Z","cross_cats_sorted":[],"title_canon_sha256":"b1dafa3bdde3cb366faccf681dc5427b4c4a6bcdb86f4c84b8b7e7a66a068194","abstract_canon_sha256":"f4f4562cc52dd634387f18877d52785baf0c90cd882f541cf9e2c9c6d9509f54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:57.859745Z","signature_b64":"tMNZynkL8f9/OogNHBirT2A2qJ0+irKueNB+73fQiu0sQUgeMhZ9TuyyVmviXNvZsQ0yCcVTSBSvJseiCtHSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c0341c161313923df747dbef2690c6c4f17fcee250f65333bbe5b2f6255c57d","last_reissued_at":"2026-07-05T08:44:57.859303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:57.859303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monocular Occupancy Prediction for Scalable Indoor Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxiao Yu, Yuntao Chen, Yuqi Wang, Zhaoxiang Zhang","submitted_at":"2024-07-16T13:50:40Z","abstract_excerpt":"Camera-based 3D occupancy prediction has recently garnered increasing attention in outdoor driving scenes. However, research in indoor scenes remains relatively unexplored. The core differences in indoor scenes lie in the complexity of scene scale and the variance in object size. In this paper, we propose a novel method, named ISO, for predicting indoor scene occupancy using monocular images. ISO harnesses the advantages of a pretrained depth model to achieve accurate depth predictions. Furthermore, we introduce the Dual Feature Line of Sight Projection (D-FLoSP) module within ISO, which enhan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11730","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.11730/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.11730","created_at":"2026-07-05T08:44:57.859378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11730v2","created_at":"2026-07-05T08:44:57.859378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11730","created_at":"2026-07-05T08:44:57.859378+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQBUDQLBGE4S","created_at":"2026-07-05T08:44:57.859378+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQBUDQLBGE4SHX3U","created_at":"2026-07-05T08:44:57.859378+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQBUDQLB","created_at":"2026-07-05T08:44:57.859378+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25059","citing_title":"VEOcc: Voxel-Centric Online Semantic Occupancy Prediction For Embodied Scene Understanding","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQBUDQLBGE4SHX3UPW7PE2IMNR","json":"https://pith.science/pith/LQBUDQLBGE4SHX3UPW7PE2IMNR.json","graph_json":"https://pith.science/api/pith-number/LQBUDQLBGE4SHX3UPW7PE2IMNR/graph.json","events_json":"https://pith.science/api/pith-number/LQBUDQLBGE4SHX3UPW7PE2IMNR/events.json","paper":"https://pith.science/paper/LQBUDQLB"},"agent_actions":{"view_html":"https://pith.science/pith/LQBUDQLBGE4SHX3UPW7PE2IMNR","download_json":"https://pith.science/pith/LQBUDQLBGE4SHX3UPW7PE2IMNR.json","view_paper":"https://pith.science/paper/LQBUDQLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11730&json=true","fetch_graph":"https://pith.science/api/pith-number/LQBUDQLBGE4SHX3UPW7PE2IMNR/graph.json","fetch_events":"https://pith.science/api/pith-number/LQBUDQLBGE4SHX3UPW7PE2IMNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQBUDQLBGE4SHX3UPW7PE2IMNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQBUDQLBGE4SHX3UPW7PE2IMNR/action/storage_attestation","attest_author":"https://pith.science/pith/LQBUDQLBGE4SHX3UPW7PE2IMNR/action/author_attestation","sign_citation":"https://pith.science/pith/LQBUDQLBGE4SHX3UPW7PE2IMNR/action/citation_signature","submit_replication":"https://pith.science/pith/LQBUDQLBGE4SHX3UPW7PE2IMNR/action/replication_record"}},"created_at":"2026-07-05T08:44:57.859378+00:00","updated_at":"2026-07-05T08:44:57.859378+00:00"}