{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IZ54LRCLTZOJGCGGF7OVUFHTTO","short_pith_number":"pith:IZ54LRCL","schema_version":"1.0","canonical_sha256":"467bc5c44b9e5c9308c62fdd5a14f39b93083a5a8cd7ca5a37f8008233222950","source":{"kind":"arxiv","id":"2412.16155","version":1},"attestation_state":"computed","paper":{"title":"Can Generative Video Models Help Pose Estimation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jason Y. Zhang, Noah Snavely, Philipp Henzler, Ricardo Martin-Brualla, Ruojin Cai, Zhengqi Li","submitted_at":"2024-12-20T18:58:24Z","abstract_excerpt":"Pairwise pose estimation from images with little or no overlap is an open challenge in computer vision. Existing methods, even those trained on large-scale datasets, struggle in these scenarios due to the lack of identifiable correspondences or visual overlap. Inspired by the human ability to infer spatial relationships from diverse scenes, we propose a novel approach, InterPose, that leverages the rich priors encoded within pre-trained generative video models. We propose to use a video model to hallucinate intermediate frames between two input images, effectively creating a dense, visual tran"},"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":"2412.16155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T18:58:24Z","cross_cats_sorted":[],"title_canon_sha256":"cb5e82b9571fc2239f01f5f7b2124ed693b190a972d222ca7c8cb9e273e97a4e","abstract_canon_sha256":"5bfac707f00da43a000fd082aeb4a527b03e14be850301ad07dabcc0b6fbbcc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:35.845378Z","signature_b64":"aIfkErLGKCbFs9jyyyWvoyMKRI0w6LLJ9X/qHvgRjUJBKxEfb/qBynIrOR6E8M9s0FlqIUAL9fdLFrJHs4d1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"467bc5c44b9e5c9308c62fdd5a14f39b93083a5a8cd7ca5a37f8008233222950","last_reissued_at":"2026-07-05T09:52:35.844973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:35.844973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Generative Video Models Help Pose Estimation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jason Y. Zhang, Noah Snavely, Philipp Henzler, Ricardo Martin-Brualla, Ruojin Cai, Zhengqi Li","submitted_at":"2024-12-20T18:58:24Z","abstract_excerpt":"Pairwise pose estimation from images with little or no overlap is an open challenge in computer vision. Existing methods, even those trained on large-scale datasets, struggle in these scenarios due to the lack of identifiable correspondences or visual overlap. Inspired by the human ability to infer spatial relationships from diverse scenes, we propose a novel approach, InterPose, that leverages the rich priors encoded within pre-trained generative video models. We propose to use a video model to hallucinate intermediate frames between two input images, effectively creating a dense, visual tran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16155","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.16155/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":"2412.16155","created_at":"2026-07-05T09:52:35.845031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16155v1","created_at":"2026-07-05T09:52:35.845031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16155","created_at":"2026-07-05T09:52:35.845031+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZ54LRCLTZOJ","created_at":"2026-07-05T09:52:35.845031+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZ54LRCLTZOJGCGG","created_at":"2026-07-05T09:52:35.845031+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZ54LRCL","created_at":"2026-07-05T09:52:35.845031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17220","citing_title":"Emergent Temporal Correspondences from Video Diffusion Transformers","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IZ54LRCLTZOJGCGGF7OVUFHTTO","json":"https://pith.science/pith/IZ54LRCLTZOJGCGGF7OVUFHTTO.json","graph_json":"https://pith.science/api/pith-number/IZ54LRCLTZOJGCGGF7OVUFHTTO/graph.json","events_json":"https://pith.science/api/pith-number/IZ54LRCLTZOJGCGGF7OVUFHTTO/events.json","paper":"https://pith.science/paper/IZ54LRCL"},"agent_actions":{"view_html":"https://pith.science/pith/IZ54LRCLTZOJGCGGF7OVUFHTTO","download_json":"https://pith.science/pith/IZ54LRCLTZOJGCGGF7OVUFHTTO.json","view_paper":"https://pith.science/paper/IZ54LRCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16155&json=true","fetch_graph":"https://pith.science/api/pith-number/IZ54LRCLTZOJGCGGF7OVUFHTTO/graph.json","fetch_events":"https://pith.science/api/pith-number/IZ54LRCLTZOJGCGGF7OVUFHTTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZ54LRCLTZOJGCGGF7OVUFHTTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZ54LRCLTZOJGCGGF7OVUFHTTO/action/storage_attestation","attest_author":"https://pith.science/pith/IZ54LRCLTZOJGCGGF7OVUFHTTO/action/author_attestation","sign_citation":"https://pith.science/pith/IZ54LRCLTZOJGCGGF7OVUFHTTO/action/citation_signature","submit_replication":"https://pith.science/pith/IZ54LRCLTZOJGCGGF7OVUFHTTO/action/replication_record"}},"created_at":"2026-07-05T09:52:35.845031+00:00","updated_at":"2026-07-05T09:52:35.845031+00:00"}