{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QP7QS5HTVECPODIEYVCFAS3LDH","short_pith_number":"pith:QP7QS5HT","schema_version":"1.0","canonical_sha256":"83ff0974f3a904f70d04c544504b6b19ed3cd2cc7153cfb828b3d3571cb1e9f8","source":{"kind":"arxiv","id":"2211.12194","version":2},"attestation_state":"computed","paper":{"title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Wang, Wenxuan Zhang, Xiaodong Cun, Xi Shen, Xuan Wang, Ying Shan, Yong Zhang, Yu Guo","submitted_at":"2022-11-22T11:35:07Z","abstract_excerpt":"Generating talking head videos through a face image and a piece of speech audio still contains many challenges. ie, unnatural head movement, distorted expression, and identity modification. We argue that these issues are mainly because of learning from the coupled 2D motion fields. On the other hand, explicitly using 3D information also suffers problems of stiff expression and incoherent video. We present SadTalker, which generates 3D motion coefficients (head pose, expression) of the 3DMM from audio and implicitly modulates a novel 3D-aware face render for talking head generation. To learn th"},"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":"2211.12194","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T11:35:07Z","cross_cats_sorted":[],"title_canon_sha256":"a15e2467227fbdca5484dc859504e13824b06cdb0736cf5f49d9bb4bfbce0da3","abstract_canon_sha256":"7688264e8bf3ba2892f586682d211f19fd95823f909fb4e3297d966c11cae925"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:11.248796Z","signature_b64":"CbDA4jdOVryNgKHZG9SV0418iC8nIlz9Bc+cITm4QDh0bZ4y0niys68n+tSJ+HnyXRNoltG7n7uD/FQUyZ52Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83ff0974f3a904f70d04c544504b6b19ed3cd2cc7153cfb828b3d3571cb1e9f8","last_reissued_at":"2026-07-05T05:50:11.248270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:11.248270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Wang, Wenxuan Zhang, Xiaodong Cun, Xi Shen, Xuan Wang, Ying Shan, Yong Zhang, Yu Guo","submitted_at":"2022-11-22T11:35:07Z","abstract_excerpt":"Generating talking head videos through a face image and a piece of speech audio still contains many challenges. ie, unnatural head movement, distorted expression, and identity modification. We argue that these issues are mainly because of learning from the coupled 2D motion fields. On the other hand, explicitly using 3D information also suffers problems of stiff expression and incoherent video. We present SadTalker, which generates 3D motion coefficients (head pose, expression) of the 3DMM from audio and implicitly modulates a novel 3D-aware face render for talking head generation. To learn th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12194","kind":"arxiv","version":2},"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/2211.12194/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":"2211.12194","created_at":"2026-07-05T05:50:11.248349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12194v2","created_at":"2026-07-05T05:50:11.248349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12194","created_at":"2026-07-05T05:50:11.248349+00:00"},{"alias_kind":"pith_short_12","alias_value":"QP7QS5HTVECP","created_at":"2026-07-05T05:50:11.248349+00:00"},{"alias_kind":"pith_short_16","alias_value":"QP7QS5HTVECPODIE","created_at":"2026-07-05T05:50:11.248349+00:00"},{"alias_kind":"pith_short_8","alias_value":"QP7QS5HT","created_at":"2026-07-05T05:50:11.248349+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05896","citing_title":"Resonant Minds: Closed-Loop Social Avatars with Theory of Mind","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08405","citing_title":"SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QP7QS5HTVECPODIEYVCFAS3LDH","json":"https://pith.science/pith/QP7QS5HTVECPODIEYVCFAS3LDH.json","graph_json":"https://pith.science/api/pith-number/QP7QS5HTVECPODIEYVCFAS3LDH/graph.json","events_json":"https://pith.science/api/pith-number/QP7QS5HTVECPODIEYVCFAS3LDH/events.json","paper":"https://pith.science/paper/QP7QS5HT"},"agent_actions":{"view_html":"https://pith.science/pith/QP7QS5HTVECPODIEYVCFAS3LDH","download_json":"https://pith.science/pith/QP7QS5HTVECPODIEYVCFAS3LDH.json","view_paper":"https://pith.science/paper/QP7QS5HT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12194&json=true","fetch_graph":"https://pith.science/api/pith-number/QP7QS5HTVECPODIEYVCFAS3LDH/graph.json","fetch_events":"https://pith.science/api/pith-number/QP7QS5HTVECPODIEYVCFAS3LDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QP7QS5HTVECPODIEYVCFAS3LDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QP7QS5HTVECPODIEYVCFAS3LDH/action/storage_attestation","attest_author":"https://pith.science/pith/QP7QS5HTVECPODIEYVCFAS3LDH/action/author_attestation","sign_citation":"https://pith.science/pith/QP7QS5HTVECPODIEYVCFAS3LDH/action/citation_signature","submit_replication":"https://pith.science/pith/QP7QS5HTVECPODIEYVCFAS3LDH/action/replication_record"}},"created_at":"2026-07-05T05:50:11.248349+00:00","updated_at":"2026-07-05T05:50:11.248349+00:00"}