{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OBTNRLRWPCJICE3UMTXFHNLXBI","short_pith_number":"pith:OBTNRLRW","schema_version":"1.0","canonical_sha256":"7066d8ae36789281137464ee53b5770a1097e6b5148d833b2bcdca8931a1a657","source":{"kind":"arxiv","id":"1704.07804","version":1},"attestation_state":"computed","paper":{"title":"SfM-Net: Learning of Structure and Motion from Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Katerina Fragkiadaki, Rahul Sukthankar, Sudheendra Vijayanarasimhan, Susanna Ricco","submitted_at":"2017-04-25T17:30:05Z","abstract_excerpt":"We propose SfM-Net, a geometry-aware neural network for motion estimation in videos that decomposes frame-to-frame pixel motion in terms of scene and object depth, camera motion and 3D object rotations and translations. Given a sequence of frames, SfM-Net predicts depth, segmentation, camera and rigid object motions, converts those into a dense frame-to-frame motion field (optical flow), differentiably warps frames in time to match pixels and back-propagates. The model can be trained with various degrees of supervision: 1) self-supervised by the re-projection photometric error (completely unsu"},"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":"1704.07804","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-25T17:30:05Z","cross_cats_sorted":[],"title_canon_sha256":"70ab5d2320746f98900d70df99ba1bf0168a5a1492237308231c3378b4f82dff","abstract_canon_sha256":"d20113401453bcc346260f54c76610682f62f33c010a5a008ffb153f16e9f3be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:36.858299Z","signature_b64":"226VxLyI6dgi3l9kkdmiGNBuVlUBr02O9kC3t83URc4cakuJ6/+8L93qwB4mMS3Pv4PHEj7f9MrROZ6ukzRkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7066d8ae36789281137464ee53b5770a1097e6b5148d833b2bcdca8931a1a657","last_reissued_at":"2026-05-18T00:45:36.857488Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:36.857488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SfM-Net: Learning of Structure and Motion from Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Katerina Fragkiadaki, Rahul Sukthankar, Sudheendra Vijayanarasimhan, Susanna Ricco","submitted_at":"2017-04-25T17:30:05Z","abstract_excerpt":"We propose SfM-Net, a geometry-aware neural network for motion estimation in videos that decomposes frame-to-frame pixel motion in terms of scene and object depth, camera motion and 3D object rotations and translations. Given a sequence of frames, SfM-Net predicts depth, segmentation, camera and rigid object motions, converts those into a dense frame-to-frame motion field (optical flow), differentiably warps frames in time to match pixels and back-propagates. The model can be trained with various degrees of supervision: 1) self-supervised by the re-projection photometric error (completely unsu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.07804","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1704.07804","created_at":"2026-05-18T00:45:36.857731+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.07804v1","created_at":"2026-05-18T00:45:36.857731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.07804","created_at":"2026-05-18T00:45:36.857731+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBTNRLRWPCJI","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBTNRLRWPCJICE3U","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBTNRLRW","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.10226","citing_title":"Movement science needs different pose tracking algorithms","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"1805.09817","citing_title":"Stereo Magnification: Learning View Synthesis using Multiplane Images","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBTNRLRWPCJICE3UMTXFHNLXBI","json":"https://pith.science/pith/OBTNRLRWPCJICE3UMTXFHNLXBI.json","graph_json":"https://pith.science/api/pith-number/OBTNRLRWPCJICE3UMTXFHNLXBI/graph.json","events_json":"https://pith.science/api/pith-number/OBTNRLRWPCJICE3UMTXFHNLXBI/events.json","paper":"https://pith.science/paper/OBTNRLRW"},"agent_actions":{"view_html":"https://pith.science/pith/OBTNRLRWPCJICE3UMTXFHNLXBI","download_json":"https://pith.science/pith/OBTNRLRWPCJICE3UMTXFHNLXBI.json","view_paper":"https://pith.science/paper/OBTNRLRW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.07804&json=true","fetch_graph":"https://pith.science/api/pith-number/OBTNRLRWPCJICE3UMTXFHNLXBI/graph.json","fetch_events":"https://pith.science/api/pith-number/OBTNRLRWPCJICE3UMTXFHNLXBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBTNRLRWPCJICE3UMTXFHNLXBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBTNRLRWPCJICE3UMTXFHNLXBI/action/storage_attestation","attest_author":"https://pith.science/pith/OBTNRLRWPCJICE3UMTXFHNLXBI/action/author_attestation","sign_citation":"https://pith.science/pith/OBTNRLRWPCJICE3UMTXFHNLXBI/action/citation_signature","submit_replication":"https://pith.science/pith/OBTNRLRWPCJICE3UMTXFHNLXBI/action/replication_record"}},"created_at":"2026-05-18T00:45:36.857731+00:00","updated_at":"2026-05-18T00:45:36.857731+00:00"}