{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NSEAMKFR5BXFYUXNJENTSP75RP","short_pith_number":"pith:NSEAMKFR","schema_version":"1.0","canonical_sha256":"6c880628b1e86e5c52ed491b393ffd8be38b82ca93be865ee3cbb837c364c104","source":{"kind":"arxiv","id":"2505.23085","version":1},"attestation_state":"computed","paper":{"title":"GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.CV","authors_text":"Gwanghyun Kim, Jan Kautz, Koki Nagano, Se Young Chun, Tianye Li, Umar Iqbal, Xueting Li, Ye Yuan","submitted_at":"2025-05-29T04:41:04Z","abstract_excerpt":"Estimating accurate and temporally consistent 3D human geometry from videos is a challenging problem in computer vision. Existing methods, primarily optimized for single images, often suffer from temporal inconsistencies and fail to capture fine-grained dynamic details. To address these limitations, we present GeoMan, a novel architecture designed to produce accurate and temporally consistent depth and normal estimations from monocular human videos. GeoMan addresses two key challenges: the scarcity of high-quality 4D training data and the need for metric depth estimation to accurately model hu"},"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":"2505.23085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T04:41:04Z","cross_cats_sorted":["cs.AI","eess.IV"],"title_canon_sha256":"206d00d448f03c9379ed52de2a6c09779dad7ab8e0d89690614cd8e7d6f4061a","abstract_canon_sha256":"4b36a4232ad1a385e8a4872b9ec5c4b7a963af525f66c4d3f82ea7a0ca9e0565"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:55.249306Z","signature_b64":"7SsgnBB5V1Yu8Sg6FPo/jDgCLrZRbo/6j7amqUyjuv2tLaXpI9/XDKUHUX8Qm2/kRhe5vVl68FA0adnT3J/6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c880628b1e86e5c52ed491b393ffd8be38b82ca93be865ee3cbb837c364c104","last_reissued_at":"2026-07-05T11:11:55.248816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:55.248816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.CV","authors_text":"Gwanghyun Kim, Jan Kautz, Koki Nagano, Se Young Chun, Tianye Li, Umar Iqbal, Xueting Li, Ye Yuan","submitted_at":"2025-05-29T04:41:04Z","abstract_excerpt":"Estimating accurate and temporally consistent 3D human geometry from videos is a challenging problem in computer vision. Existing methods, primarily optimized for single images, often suffer from temporal inconsistencies and fail to capture fine-grained dynamic details. To address these limitations, we present GeoMan, a novel architecture designed to produce accurate and temporally consistent depth and normal estimations from monocular human videos. GeoMan addresses two key challenges: the scarcity of high-quality 4D training data and the need for metric depth estimation to accurately model hu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23085","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/2505.23085/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":"2505.23085","created_at":"2026-07-05T11:11:55.248869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23085v1","created_at":"2026-07-05T11:11:55.248869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23085","created_at":"2026-07-05T11:11:55.248869+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSEAMKFR5BXF","created_at":"2026-07-05T11:11:55.248869+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSEAMKFR5BXFYUXN","created_at":"2026-07-05T11:11:55.248869+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSEAMKFR","created_at":"2026-07-05T11:11:55.248869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21681","citing_title":"Sapiens2","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NSEAMKFR5BXFYUXNJENTSP75RP","json":"https://pith.science/pith/NSEAMKFR5BXFYUXNJENTSP75RP.json","graph_json":"https://pith.science/api/pith-number/NSEAMKFR5BXFYUXNJENTSP75RP/graph.json","events_json":"https://pith.science/api/pith-number/NSEAMKFR5BXFYUXNJENTSP75RP/events.json","paper":"https://pith.science/paper/NSEAMKFR"},"agent_actions":{"view_html":"https://pith.science/pith/NSEAMKFR5BXFYUXNJENTSP75RP","download_json":"https://pith.science/pith/NSEAMKFR5BXFYUXNJENTSP75RP.json","view_paper":"https://pith.science/paper/NSEAMKFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23085&json=true","fetch_graph":"https://pith.science/api/pith-number/NSEAMKFR5BXFYUXNJENTSP75RP/graph.json","fetch_events":"https://pith.science/api/pith-number/NSEAMKFR5BXFYUXNJENTSP75RP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSEAMKFR5BXFYUXNJENTSP75RP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSEAMKFR5BXFYUXNJENTSP75RP/action/storage_attestation","attest_author":"https://pith.science/pith/NSEAMKFR5BXFYUXNJENTSP75RP/action/author_attestation","sign_citation":"https://pith.science/pith/NSEAMKFR5BXFYUXNJENTSP75RP/action/citation_signature","submit_replication":"https://pith.science/pith/NSEAMKFR5BXFYUXNJENTSP75RP/action/replication_record"}},"created_at":"2026-07-05T11:11:55.248869+00:00","updated_at":"2026-07-05T11:11:55.248869+00:00"}