{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CWIANV4XI47UNDFTLYEDBTYTBV","short_pith_number":"pith:CWIANV4X","schema_version":"1.0","canonical_sha256":"159006d797473f468cb35e0830cf130d5bf4486a8c8c8101019f74d69ab14b9b","source":{"kind":"arxiv","id":"2606.13364","version":1},"attestation_state":"computed","paper":{"title":"VideoMDM: Towards 3D Human Motion Generation From 2D Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amir Mann, Gal Michael Harari, Merav Keidar, Or Litany","submitted_at":"2026-06-11T13:49:23Z","abstract_excerpt":"We introduce VideoMDM, a diffusion-based framework that trains 3D human motion priors directly from accurate 2D poses extracted from monocular videos, without any 3D ground truth. A pretrained 2D-to-3D lifter provides approximate 3D pose sequences that serve as a noisy teacher: these are diffused, denoised by the model in 3D, and supervised in 2D by reprojecting the prediction and comparing against accurate keypoints. We show that, under mild assumptions, a depth-weighted 2D reprojection loss is equivalent in expectation to direct 3D supervision, and we adapt standard 3D motion regularizers - "},"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":"2606.13364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T13:49:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f181c847fb75c1ddb9e6b76eb2703656fef7c0d64a94128b7e70715790ef7377","abstract_canon_sha256":"e194e91a70bc461e3a42f9b560fe5298397042c13745e3da514fe2fd6b2af324"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:57.658309Z","signature_b64":"/BF7M1/EdlU4mo7Qi0KF09hv/2HoQPVaHxTstv/HESV5VT27rObVHetdDnAO/rc9315MAIQulDS83C5Tp1axDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"159006d797473f468cb35e0830cf130d5bf4486a8c8c8101019f74d69ab14b9b","last_reissued_at":"2026-06-12T01:09:57.657357Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:57.657357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoMDM: Towards 3D Human Motion Generation From 2D Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amir Mann, Gal Michael Harari, Merav Keidar, Or Litany","submitted_at":"2026-06-11T13:49:23Z","abstract_excerpt":"We introduce VideoMDM, a diffusion-based framework that trains 3D human motion priors directly from accurate 2D poses extracted from monocular videos, without any 3D ground truth. A pretrained 2D-to-3D lifter provides approximate 3D pose sequences that serve as a noisy teacher: these are diffused, denoised by the model in 3D, and supervised in 2D by reprojecting the prediction and comparing against accurate keypoints. We show that, under mild assumptions, a depth-weighted 2D reprojection loss is equivalent in expectation to direct 3D supervision, and we adapt standard 3D motion regularizers - "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13364","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/2606.13364/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":"2606.13364","created_at":"2026-06-12T01:09:57.657539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13364v1","created_at":"2026-06-12T01:09:57.657539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13364","created_at":"2026-06-12T01:09:57.657539+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWIANV4XI47U","created_at":"2026-06-12T01:09:57.657539+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWIANV4XI47UNDFT","created_at":"2026-06-12T01:09:57.657539+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWIANV4X","created_at":"2026-06-12T01:09:57.657539+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/CWIANV4XI47UNDFTLYEDBTYTBV","json":"https://pith.science/pith/CWIANV4XI47UNDFTLYEDBTYTBV.json","graph_json":"https://pith.science/api/pith-number/CWIANV4XI47UNDFTLYEDBTYTBV/graph.json","events_json":"https://pith.science/api/pith-number/CWIANV4XI47UNDFTLYEDBTYTBV/events.json","paper":"https://pith.science/paper/CWIANV4X"},"agent_actions":{"view_html":"https://pith.science/pith/CWIANV4XI47UNDFTLYEDBTYTBV","download_json":"https://pith.science/pith/CWIANV4XI47UNDFTLYEDBTYTBV.json","view_paper":"https://pith.science/paper/CWIANV4X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13364&json=true","fetch_graph":"https://pith.science/api/pith-number/CWIANV4XI47UNDFTLYEDBTYTBV/graph.json","fetch_events":"https://pith.science/api/pith-number/CWIANV4XI47UNDFTLYEDBTYTBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWIANV4XI47UNDFTLYEDBTYTBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWIANV4XI47UNDFTLYEDBTYTBV/action/storage_attestation","attest_author":"https://pith.science/pith/CWIANV4XI47UNDFTLYEDBTYTBV/action/author_attestation","sign_citation":"https://pith.science/pith/CWIANV4XI47UNDFTLYEDBTYTBV/action/citation_signature","submit_replication":"https://pith.science/pith/CWIANV4XI47UNDFTLYEDBTYTBV/action/replication_record"}},"created_at":"2026-06-12T01:09:57.657539+00:00","updated_at":"2026-06-12T01:09:57.657539+00:00"}