{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZVFCWEYBONX6L64GT5TVSVRMLF","short_pith_number":"pith:ZVFCWEYB","schema_version":"1.0","canonical_sha256":"cd4a2b1301736fe5fb869f6759562c597a09e8b9593cd51c53a2d1820e24d34f","source":{"kind":"arxiv","id":"2305.00787","version":1},"attestation_state":"computed","paper":{"title":"GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiawei Huang, Jinglin Liu, Jinzheng He, Rongjie Huang, Xiang Yin, Yi Ren, Zejun Ma, Zhenhui Ye, Zhou Zhao, Ziyue Jiang","submitted_at":"2023-05-01T12:24:09Z","abstract_excerpt":"Generating talking person portraits with arbitrary speech audio is a crucial problem in the field of digital human and metaverse. A modern talking face generation method is expected to achieve the goals of generalized audio-lip synchronization, good video quality, and high system efficiency. Recently, neural radiance field (NeRF) has become a popular rendering technique in this field since it could achieve high-fidelity and 3D-consistent talking face generation with a few-minute-long training video. However, there still exist several challenges for NeRF-based methods: 1) as for the lip synchro"},"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":"2305.00787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-01T12:24:09Z","cross_cats_sorted":[],"title_canon_sha256":"ecc068bb29d84bda54db724a12d3334d52d4e55110502ef5091a5f3e58cc3718","abstract_canon_sha256":"26922a68f8fd08ddbb239684e7712cd328737568b674bb0e1863ef7fdb1b053c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:45.219907Z","signature_b64":"k6I/Q8RCgLZp5mSuXrRRWM4DR6dlCvoB30mrzC0lzEXlggGoKFzxo+TjIHv14JP4rkfud9jENBXWU7bff3pXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd4a2b1301736fe5fb869f6759562c597a09e8b9593cd51c53a2d1820e24d34f","last_reissued_at":"2026-07-05T06:05:45.219430Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:45.219430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiawei Huang, Jinglin Liu, Jinzheng He, Rongjie Huang, Xiang Yin, Yi Ren, Zejun Ma, Zhenhui Ye, Zhou Zhao, Ziyue Jiang","submitted_at":"2023-05-01T12:24:09Z","abstract_excerpt":"Generating talking person portraits with arbitrary speech audio is a crucial problem in the field of digital human and metaverse. A modern talking face generation method is expected to achieve the goals of generalized audio-lip synchronization, good video quality, and high system efficiency. Recently, neural radiance field (NeRF) has become a popular rendering technique in this field since it could achieve high-fidelity and 3D-consistent talking face generation with a few-minute-long training video. However, there still exist several challenges for NeRF-based methods: 1) as for the lip synchro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00787","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/2305.00787/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":"2305.00787","created_at":"2026-07-05T06:05:45.219489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.00787v1","created_at":"2026-07-05T06:05:45.219489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00787","created_at":"2026-07-05T06:05:45.219489+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVFCWEYBONX6","created_at":"2026-07-05T06:05:45.219489+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVFCWEYBONX6L64G","created_at":"2026-07-05T06:05:45.219489+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVFCWEYB","created_at":"2026-07-05T06:05:45.219489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.09209","citing_title":"JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23586","citing_title":"Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZVFCWEYBONX6L64GT5TVSVRMLF","json":"https://pith.science/pith/ZVFCWEYBONX6L64GT5TVSVRMLF.json","graph_json":"https://pith.science/api/pith-number/ZVFCWEYBONX6L64GT5TVSVRMLF/graph.json","events_json":"https://pith.science/api/pith-number/ZVFCWEYBONX6L64GT5TVSVRMLF/events.json","paper":"https://pith.science/paper/ZVFCWEYB"},"agent_actions":{"view_html":"https://pith.science/pith/ZVFCWEYBONX6L64GT5TVSVRMLF","download_json":"https://pith.science/pith/ZVFCWEYBONX6L64GT5TVSVRMLF.json","view_paper":"https://pith.science/paper/ZVFCWEYB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.00787&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVFCWEYBONX6L64GT5TVSVRMLF/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVFCWEYBONX6L64GT5TVSVRMLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVFCWEYBONX6L64GT5TVSVRMLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVFCWEYBONX6L64GT5TVSVRMLF/action/storage_attestation","attest_author":"https://pith.science/pith/ZVFCWEYBONX6L64GT5TVSVRMLF/action/author_attestation","sign_citation":"https://pith.science/pith/ZVFCWEYBONX6L64GT5TVSVRMLF/action/citation_signature","submit_replication":"https://pith.science/pith/ZVFCWEYBONX6L64GT5TVSVRMLF/action/replication_record"}},"created_at":"2026-07-05T06:05:45.219489+00:00","updated_at":"2026-07-05T06:05:45.219489+00:00"}