{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MUT4BDLYEVTGGCN7LPEJK56DCI","short_pith_number":"pith:MUT4BDLY","schema_version":"1.0","canonical_sha256":"6527c08d7825666309bf5bc89577c3123af350ec28d880bdba80046058966f29","source":{"kind":"arxiv","id":"2408.03284","version":1},"attestation_state":"computed","paper":{"title":"ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Borong Liang, Errui Ding, Hang Zhou, Haocheng Feng, Jiazhi Guan, Jingdong Wang, Jingtuo Liu, Kaisiyuan Wang, Shengyi He, Youjian Zhao, Zhanwang Zhang, Zhiliang Xu, Ziwei Liu","submitted_at":"2024-08-06T16:31:45Z","abstract_excerpt":"Lip-syncing videos with given audio is the foundation for various applications including the creation of virtual presenters or performers. While recent studies explore high-fidelity lip-sync with different techniques, their task-orientated models either require long-term videos for clip-specific training or retain visible artifacts. In this paper, we propose a unified and effective framework ReSyncer, that synchronizes generalized audio-visual facial information. The key design is revisiting and rewiring the Style-based generator to efficiently adopt 3D facial dynamics predicted by a principle"},"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":"2408.03284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-06T16:31:45Z","cross_cats_sorted":["cs.GR","cs.MM"],"title_canon_sha256":"141b70283654817c98e04a16e48b2ea4889f7d948be9e13bc32f590ff50fcac6","abstract_canon_sha256":"e30eb94a3e93b838ff9473e480004b4a9a2ce5dcff89a84a01834aa5d983ce62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:48.498276Z","signature_b64":"o+cYdri+sb4LUmnw16GtNTnDAMklRPdCE07f0/M2is+01zFfJ9jOK1bO8gcGm8d1DRZSo9osIisrEtiWEmXuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6527c08d7825666309bf5bc89577c3123af350ec28d880bdba80046058966f29","last_reissued_at":"2026-07-05T08:52:48.497894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:48.497894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Borong Liang, Errui Ding, Hang Zhou, Haocheng Feng, Jiazhi Guan, Jingdong Wang, Jingtuo Liu, Kaisiyuan Wang, Shengyi He, Youjian Zhao, Zhanwang Zhang, Zhiliang Xu, Ziwei Liu","submitted_at":"2024-08-06T16:31:45Z","abstract_excerpt":"Lip-syncing videos with given audio is the foundation for various applications including the creation of virtual presenters or performers. While recent studies explore high-fidelity lip-sync with different techniques, their task-orientated models either require long-term videos for clip-specific training or retain visible artifacts. In this paper, we propose a unified and effective framework ReSyncer, that synchronizes generalized audio-visual facial information. The key design is revisiting and rewiring the Style-based generator to efficiently adopt 3D facial dynamics predicted by a principle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03284","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/2408.03284/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":"2408.03284","created_at":"2026-07-05T08:52:48.497948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.03284v1","created_at":"2026-07-05T08:52:48.497948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03284","created_at":"2026-07-05T08:52:48.497948+00:00"},{"alias_kind":"pith_short_12","alias_value":"MUT4BDLYEVTG","created_at":"2026-07-05T08:52:48.497948+00:00"},{"alias_kind":"pith_short_16","alias_value":"MUT4BDLYEVTGGCN7","created_at":"2026-07-05T08:52:48.497948+00:00"},{"alias_kind":"pith_short_8","alias_value":"MUT4BDLY","created_at":"2026-07-05T08:52:48.497948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01390","citing_title":"FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MUT4BDLYEVTGGCN7LPEJK56DCI","json":"https://pith.science/pith/MUT4BDLYEVTGGCN7LPEJK56DCI.json","graph_json":"https://pith.science/api/pith-number/MUT4BDLYEVTGGCN7LPEJK56DCI/graph.json","events_json":"https://pith.science/api/pith-number/MUT4BDLYEVTGGCN7LPEJK56DCI/events.json","paper":"https://pith.science/paper/MUT4BDLY"},"agent_actions":{"view_html":"https://pith.science/pith/MUT4BDLYEVTGGCN7LPEJK56DCI","download_json":"https://pith.science/pith/MUT4BDLYEVTGGCN7LPEJK56DCI.json","view_paper":"https://pith.science/paper/MUT4BDLY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.03284&json=true","fetch_graph":"https://pith.science/api/pith-number/MUT4BDLYEVTGGCN7LPEJK56DCI/graph.json","fetch_events":"https://pith.science/api/pith-number/MUT4BDLYEVTGGCN7LPEJK56DCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MUT4BDLYEVTGGCN7LPEJK56DCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MUT4BDLYEVTGGCN7LPEJK56DCI/action/storage_attestation","attest_author":"https://pith.science/pith/MUT4BDLYEVTGGCN7LPEJK56DCI/action/author_attestation","sign_citation":"https://pith.science/pith/MUT4BDLYEVTGGCN7LPEJK56DCI/action/citation_signature","submit_replication":"https://pith.science/pith/MUT4BDLYEVTGGCN7LPEJK56DCI/action/replication_record"}},"created_at":"2026-07-05T08:52:48.497948+00:00","updated_at":"2026-07-05T08:52:48.497948+00:00"}