{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VY2EQUP5FAX7ELS4S4JUZKCUS2","short_pith_number":"pith:VY2EQUP5","schema_version":"1.0","canonical_sha256":"ae344851fd282ff22e5c97134ca854968e653128630b37d3cba98598c988b3e0","source":{"kind":"arxiv","id":"2605.15583","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised 3D Human Pose Estimation via Conditional Multi-view Ancestral Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fumio Okura, Ryohei Goto, Shunsuke Saruwatari, Takuya Fujihashi","submitted_at":"2026-05-15T03:47:04Z","abstract_excerpt":"We propose a method of estimating a 3D human pose from a single view without 3D supervision. The key to our method is to leverage the 2D diffusion priors of motion diffusion models (MDMs) pre-trained on large 2D human pose datasets. Specifically, we extend multi-view ancestral sampling of diffusion models to the task of 2D-3D lifting of human pose. To this end, we newly propose a conditional multi-view ancestral sampling (cMAS) that optimizes the 3D pose such that its multi-view projections follow the manifold in 2D MDM noise space, while conditioning the 3D pose to match the given 2D poses an"},"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":"2605.15583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T03:47:04Z","cross_cats_sorted":[],"title_canon_sha256":"076e47769b9cf74647fd574b7251a2aa4e4a4fd0875cd5f21e6bc41e09aa27a9","abstract_canon_sha256":"cdd1a8afa1b3bfc1354d0579ee8d2c4fa0951255e9e877100991248f7c85de33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:06.593774Z","signature_b64":"qXId5VSGJTfZibUX0FJyxNGr+dohE+sHRFYMjohzRvZ89efinJYilU97cM6mEtFbjfICsbi9IZ3M/WaDttBrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae344851fd282ff22e5c97134ca854968e653128630b37d3cba98598c988b3e0","last_reissued_at":"2026-05-20T00:01:06.592696Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:06.592696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised 3D Human Pose Estimation via Conditional Multi-view Ancestral Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fumio Okura, Ryohei Goto, Shunsuke Saruwatari, Takuya Fujihashi","submitted_at":"2026-05-15T03:47:04Z","abstract_excerpt":"We propose a method of estimating a 3D human pose from a single view without 3D supervision. The key to our method is to leverage the 2D diffusion priors of motion diffusion models (MDMs) pre-trained on large 2D human pose datasets. Specifically, we extend multi-view ancestral sampling of diffusion models to the task of 2D-3D lifting of human pose. To this end, we newly propose a conditional multi-view ancestral sampling (cMAS) that optimizes the 3D pose such that its multi-view projections follow the manifold in 2D MDM noise space, while conditioning the 3D pose to match the given 2D poses an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15583","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/2605.15583/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:35.246401Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.068268Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b46c0429ea4c9c78c98ce63427d0578bb188a0e13748b3bc0b19b5952579f7a8"},"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":"2605.15583","created_at":"2026-05-20T00:01:06.592990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15583v1","created_at":"2026-05-20T00:01:06.592990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15583","created_at":"2026-05-20T00:01:06.592990+00:00"},{"alias_kind":"pith_short_12","alias_value":"VY2EQUP5FAX7","created_at":"2026-05-20T00:01:06.592990+00:00"},{"alias_kind":"pith_short_16","alias_value":"VY2EQUP5FAX7ELS4","created_at":"2026-05-20T00:01:06.592990+00:00"},{"alias_kind":"pith_short_8","alias_value":"VY2EQUP5","created_at":"2026-05-20T00:01:06.592990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VY2EQUP5FAX7ELS4S4JUZKCUS2","json":"https://pith.science/pith/VY2EQUP5FAX7ELS4S4JUZKCUS2.json","graph_json":"https://pith.science/api/pith-number/VY2EQUP5FAX7ELS4S4JUZKCUS2/graph.json","events_json":"https://pith.science/api/pith-number/VY2EQUP5FAX7ELS4S4JUZKCUS2/events.json","paper":"https://pith.science/paper/VY2EQUP5"},"agent_actions":{"view_html":"https://pith.science/pith/VY2EQUP5FAX7ELS4S4JUZKCUS2","download_json":"https://pith.science/pith/VY2EQUP5FAX7ELS4S4JUZKCUS2.json","view_paper":"https://pith.science/paper/VY2EQUP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15583&json=true","fetch_graph":"https://pith.science/api/pith-number/VY2EQUP5FAX7ELS4S4JUZKCUS2/graph.json","fetch_events":"https://pith.science/api/pith-number/VY2EQUP5FAX7ELS4S4JUZKCUS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VY2EQUP5FAX7ELS4S4JUZKCUS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VY2EQUP5FAX7ELS4S4JUZKCUS2/action/storage_attestation","attest_author":"https://pith.science/pith/VY2EQUP5FAX7ELS4S4JUZKCUS2/action/author_attestation","sign_citation":"https://pith.science/pith/VY2EQUP5FAX7ELS4S4JUZKCUS2/action/citation_signature","submit_replication":"https://pith.science/pith/VY2EQUP5FAX7ELS4S4JUZKCUS2/action/replication_record"}},"created_at":"2026-05-20T00:01:06.592990+00:00","updated_at":"2026-05-20T00:01:06.592990+00:00"}