{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FI4Z4NZY6PLBTRDBWNK6RONCOM","short_pith_number":"pith:FI4Z4NZY","schema_version":"1.0","canonical_sha256":"2a399e3738f3d619c461b355e8b9a273153bc96e4e104a90c2b472ecfbcc6481","source":{"kind":"arxiv","id":"2408.10805","version":1},"attestation_state":"computed","paper":{"title":"MPL: Lifting 3D Human Pose from Multi-view 2D Poses","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandre Alahi, Christophe De Vleeschouwer, Seyed Abolfazl Ghasemzadeh","submitted_at":"2024-08-20T12:55:14Z","abstract_excerpt":"Estimating 3D human poses from 2D images is challenging due to occlusions and projective acquisition. Learning-based approaches have been largely studied to address this challenge, both in single and multi-view setups. These solutions however fail to generalize to real-world cases due to the lack of (multi-view) 'in-the-wild' images paired with 3D poses for training. For this reason, we propose combining 2D pose estimation, for which large and rich training datasets exist, and 2D-to-3D pose lifting, using a transformer-based network that can be trained from synthetic 2D-3D pose pairs. Our expe"},"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":"2408.10805","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-20T12:55:14Z","cross_cats_sorted":[],"title_canon_sha256":"e7ce421b1baf8920b6a8b15742e22f6d8141ee48a4b5f01ae4172fb7cb09c076","abstract_canon_sha256":"d7233fb9e5c854379a227d62be5d85ea314d888bbd420bc1f7bf50052cfc2015"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:17.674861Z","signature_b64":"7uj3LqU/iPPN+b3k2+sHUXCQkg03Klb2G76aSqA8NAsUmTVqDMQ2pujsNbUYX8l2OHM2gLPWxjkLWyH2pXdCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a399e3738f3d619c461b355e8b9a273153bc96e4e104a90c2b472ecfbcc6481","last_reissued_at":"2026-07-05T08:57:17.674386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:17.674386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MPL: Lifting 3D Human Pose from Multi-view 2D Poses","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandre Alahi, Christophe De Vleeschouwer, Seyed Abolfazl Ghasemzadeh","submitted_at":"2024-08-20T12:55:14Z","abstract_excerpt":"Estimating 3D human poses from 2D images is challenging due to occlusions and projective acquisition. Learning-based approaches have been largely studied to address this challenge, both in single and multi-view setups. These solutions however fail to generalize to real-world cases due to the lack of (multi-view) 'in-the-wild' images paired with 3D poses for training. For this reason, we propose combining 2D pose estimation, for which large and rich training datasets exist, and 2D-to-3D pose lifting, using a transformer-based network that can be trained from synthetic 2D-3D pose pairs. Our expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10805","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/2408.10805/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":"2408.10805","created_at":"2026-07-05T08:57:17.674440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10805v1","created_at":"2026-07-05T08:57:17.674440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10805","created_at":"2026-07-05T08:57:17.674440+00:00"},{"alias_kind":"pith_short_12","alias_value":"FI4Z4NZY6PLB","created_at":"2026-07-05T08:57:17.674440+00:00"},{"alias_kind":"pith_short_16","alias_value":"FI4Z4NZY6PLBTRDB","created_at":"2026-07-05T08:57:17.674440+00:00"},{"alias_kind":"pith_short_8","alias_value":"FI4Z4NZY","created_at":"2026-07-05T08:57:17.674440+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/FI4Z4NZY6PLBTRDBWNK6RONCOM","json":"https://pith.science/pith/FI4Z4NZY6PLBTRDBWNK6RONCOM.json","graph_json":"https://pith.science/api/pith-number/FI4Z4NZY6PLBTRDBWNK6RONCOM/graph.json","events_json":"https://pith.science/api/pith-number/FI4Z4NZY6PLBTRDBWNK6RONCOM/events.json","paper":"https://pith.science/paper/FI4Z4NZY"},"agent_actions":{"view_html":"https://pith.science/pith/FI4Z4NZY6PLBTRDBWNK6RONCOM","download_json":"https://pith.science/pith/FI4Z4NZY6PLBTRDBWNK6RONCOM.json","view_paper":"https://pith.science/paper/FI4Z4NZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10805&json=true","fetch_graph":"https://pith.science/api/pith-number/FI4Z4NZY6PLBTRDBWNK6RONCOM/graph.json","fetch_events":"https://pith.science/api/pith-number/FI4Z4NZY6PLBTRDBWNK6RONCOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FI4Z4NZY6PLBTRDBWNK6RONCOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FI4Z4NZY6PLBTRDBWNK6RONCOM/action/storage_attestation","attest_author":"https://pith.science/pith/FI4Z4NZY6PLBTRDBWNK6RONCOM/action/author_attestation","sign_citation":"https://pith.science/pith/FI4Z4NZY6PLBTRDBWNK6RONCOM/action/citation_signature","submit_replication":"https://pith.science/pith/FI4Z4NZY6PLBTRDBWNK6RONCOM/action/replication_record"}},"created_at":"2026-07-05T08:57:17.674440+00:00","updated_at":"2026-07-05T08:57:17.674440+00:00"}