{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7T4RO47C7742Z7KT27NDJ27RTD","short_pith_number":"pith:7T4RO47C","schema_version":"1.0","canonical_sha256":"fcf91773e2fff9acfd53d7da34ebf198d51229abfa1db06a70fd5510a3f5fbe6","source":{"kind":"arxiv","id":"2412.17806","version":2},"attestation_state":"computed","paper":{"title":"Reconstructing People, Places, and Cameras","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angjoo Kanazawa, Anthony Zhang, Brent Yi, Hongsuk Choi, Jitendra Malik, Lea M\\\"uller","submitted_at":"2024-12-23T18:58:34Z","abstract_excerpt":"We present \"Humans and Structure from Motion\" (HSfM), a method for jointly reconstructing multiple human meshes, scene point clouds, and camera parameters in a metric world coordinate system from a sparse set of uncalibrated multi-view images featuring people. Our approach combines data-driven scene reconstruction with the traditional Structure-from-Motion (SfM) framework to achieve more accurate scene reconstruction and camera estimation, while simultaneously recovering human meshes. In contrast to existing scene reconstruction and SfM methods that lack metric scale information, our method es"},"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":"2412.17806","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-23T18:58:34Z","cross_cats_sorted":[],"title_canon_sha256":"98205d25f840dc690f29af9913675343cf42eed2423a2e4303800cd7f42607b8","abstract_canon_sha256":"c6eda337367485d302e5c6c9ec13d636c74e9309097612b71be7b89ff4387806"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:26.348700Z","signature_b64":"LByEGuWFy/1BOXDI6vsA8spRnenbW/7a9Ykqo5KcCVv4w5WlX8BahAIT9SGCr8RAxFgVyJCJ3H5d2gS/u/pLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcf91773e2fff9acfd53d7da34ebf198d51229abfa1db06a70fd5510a3f5fbe6","last_reissued_at":"2026-07-05T11:06:26.348069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:26.348069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reconstructing People, Places, and Cameras","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angjoo Kanazawa, Anthony Zhang, Brent Yi, Hongsuk Choi, Jitendra Malik, Lea M\\\"uller","submitted_at":"2024-12-23T18:58:34Z","abstract_excerpt":"We present \"Humans and Structure from Motion\" (HSfM), a method for jointly reconstructing multiple human meshes, scene point clouds, and camera parameters in a metric world coordinate system from a sparse set of uncalibrated multi-view images featuring people. Our approach combines data-driven scene reconstruction with the traditional Structure-from-Motion (SfM) framework to achieve more accurate scene reconstruction and camera estimation, while simultaneously recovering human meshes. In contrast to existing scene reconstruction and SfM methods that lack metric scale information, our method es"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17806","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/2412.17806/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":"2412.17806","created_at":"2026-07-05T11:06:26.348165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17806v2","created_at":"2026-07-05T11:06:26.348165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17806","created_at":"2026-07-05T11:06:26.348165+00:00"},{"alias_kind":"pith_short_12","alias_value":"7T4RO47C7742","created_at":"2026-07-05T11:06:26.348165+00:00"},{"alias_kind":"pith_short_16","alias_value":"7T4RO47C7742Z7KT","created_at":"2026-07-05T11:06:26.348165+00:00"},{"alias_kind":"pith_short_8","alias_value":"7T4RO47C","created_at":"2026-07-05T11:06:26.348165+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02350","citing_title":"TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19624","citing_title":"GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7T4RO47C7742Z7KT27NDJ27RTD","json":"https://pith.science/pith/7T4RO47C7742Z7KT27NDJ27RTD.json","graph_json":"https://pith.science/api/pith-number/7T4RO47C7742Z7KT27NDJ27RTD/graph.json","events_json":"https://pith.science/api/pith-number/7T4RO47C7742Z7KT27NDJ27RTD/events.json","paper":"https://pith.science/paper/7T4RO47C"},"agent_actions":{"view_html":"https://pith.science/pith/7T4RO47C7742Z7KT27NDJ27RTD","download_json":"https://pith.science/pith/7T4RO47C7742Z7KT27NDJ27RTD.json","view_paper":"https://pith.science/paper/7T4RO47C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17806&json=true","fetch_graph":"https://pith.science/api/pith-number/7T4RO47C7742Z7KT27NDJ27RTD/graph.json","fetch_events":"https://pith.science/api/pith-number/7T4RO47C7742Z7KT27NDJ27RTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7T4RO47C7742Z7KT27NDJ27RTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7T4RO47C7742Z7KT27NDJ27RTD/action/storage_attestation","attest_author":"https://pith.science/pith/7T4RO47C7742Z7KT27NDJ27RTD/action/author_attestation","sign_citation":"https://pith.science/pith/7T4RO47C7742Z7KT27NDJ27RTD/action/citation_signature","submit_replication":"https://pith.science/pith/7T4RO47C7742Z7KT27NDJ27RTD/action/replication_record"}},"created_at":"2026-07-05T11:06:26.348165+00:00","updated_at":"2026-07-05T11:06:26.348165+00:00"}