{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BR742OIEMEBM6JA7GCGNTY7IA4","short_pith_number":"pith:BR742OIE","schema_version":"1.0","canonical_sha256":"0c7fcd39046102cf241f308cd9e3e80705e978eebcaffdb3c6e1c4f995afd286","source":{"kind":"arxiv","id":"2411.08128","version":1},"attestation_state":"computed","paper":{"title":"CameraHMR: Aligning People with Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michael J. Black, Priyanka Patel","submitted_at":"2024-11-12T19:12:12Z","abstract_excerpt":"We address the challenge of accurate 3D human pose and shape estimation from monocular images. The key to accuracy and robustness lies in high-quality training data. Existing training datasets containing real images with pseudo ground truth (pGT) use SMPLify to fit SMPL to sparse 2D joint locations, assuming a simplified camera with default intrinsics. We make two contributions that improve pGT accuracy. First, to estimate camera intrinsics, we develop a field-of-view prediction model (HumanFoV) trained on a dataset of images containing people. We use the estimated intrinsics to enhance the 4D"},"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":"2411.08128","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T19:12:12Z","cross_cats_sorted":[],"title_canon_sha256":"062ae553fe8f7347cc0a4bab8e4df29c74fdba398945cea9f04ff7bb1a0ed0f2","abstract_canon_sha256":"1e83407dccbc8517184b989846cd7b015ecc6f8ff475d837c1d145bba651448b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:41.824881Z","signature_b64":"HIyq+KDYsL0iEHcBRYBkO9l9G8yOAoGtWNHluo2Ko6MahoIooaEPibYsbvPMqdbL1GdFoT9ErDDAAn8P790eAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c7fcd39046102cf241f308cd9e3e80705e978eebcaffdb3c6e1c4f995afd286","last_reissued_at":"2026-07-05T09:34:41.824399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:41.824399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CameraHMR: Aligning People with Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michael J. Black, Priyanka Patel","submitted_at":"2024-11-12T19:12:12Z","abstract_excerpt":"We address the challenge of accurate 3D human pose and shape estimation from monocular images. The key to accuracy and robustness lies in high-quality training data. Existing training datasets containing real images with pseudo ground truth (pGT) use SMPLify to fit SMPL to sparse 2D joint locations, assuming a simplified camera with default intrinsics. We make two contributions that improve pGT accuracy. First, to estimate camera intrinsics, we develop a field-of-view prediction model (HumanFoV) trained on a dataset of images containing people. We use the estimated intrinsics to enhance the 4D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08128","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/2411.08128/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":"2411.08128","created_at":"2026-07-05T09:34:41.824460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.08128v1","created_at":"2026-07-05T09:34:41.824460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08128","created_at":"2026-07-05T09:34:41.824460+00:00"},{"alias_kind":"pith_short_12","alias_value":"BR742OIEMEBM","created_at":"2026-07-05T09:34:41.824460+00:00"},{"alias_kind":"pith_short_16","alias_value":"BR742OIEMEBM6JA7","created_at":"2026-07-05T09:34:41.824460+00:00"},{"alias_kind":"pith_short_8","alias_value":"BR742OIE","created_at":"2026-07-05T09:34:41.824460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28820","citing_title":"CoGS: Compositional Dynamic Human-Object Scenes Gaussian Splatting from Monocular Video","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04554","citing_title":"InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BR742OIEMEBM6JA7GCGNTY7IA4","json":"https://pith.science/pith/BR742OIEMEBM6JA7GCGNTY7IA4.json","graph_json":"https://pith.science/api/pith-number/BR742OIEMEBM6JA7GCGNTY7IA4/graph.json","events_json":"https://pith.science/api/pith-number/BR742OIEMEBM6JA7GCGNTY7IA4/events.json","paper":"https://pith.science/paper/BR742OIE"},"agent_actions":{"view_html":"https://pith.science/pith/BR742OIEMEBM6JA7GCGNTY7IA4","download_json":"https://pith.science/pith/BR742OIEMEBM6JA7GCGNTY7IA4.json","view_paper":"https://pith.science/paper/BR742OIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.08128&json=true","fetch_graph":"https://pith.science/api/pith-number/BR742OIEMEBM6JA7GCGNTY7IA4/graph.json","fetch_events":"https://pith.science/api/pith-number/BR742OIEMEBM6JA7GCGNTY7IA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BR742OIEMEBM6JA7GCGNTY7IA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BR742OIEMEBM6JA7GCGNTY7IA4/action/storage_attestation","attest_author":"https://pith.science/pith/BR742OIEMEBM6JA7GCGNTY7IA4/action/author_attestation","sign_citation":"https://pith.science/pith/BR742OIEMEBM6JA7GCGNTY7IA4/action/citation_signature","submit_replication":"https://pith.science/pith/BR742OIEMEBM6JA7GCGNTY7IA4/action/replication_record"}},"created_at":"2026-07-05T09:34:41.824460+00:00","updated_at":"2026-07-05T09:34:41.824460+00:00"}