{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BFFKAAIFJGVD2JFAMFEFILRXHB","short_pith_number":"pith:BFFKAAIF","schema_version":"1.0","canonical_sha256":"094aa0010549aa3d24a06148542e373864dea7f557e1b59813face3ab6aff181","source":{"kind":"arxiv","id":"2406.18284","version":2},"attestation_state":"computed","paper":{"title":"RealTalk: Real-time and Realistic Audio-driven Face Generation with 3D Facial Prior-guided Identity Alignment Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Chuming Lin, Donghao Luo, Junwei Zhu, Xiaobin Hu, Xiaozhong Ji, Yanhao Ge, Ying Tai, Zhonggan Ding","submitted_at":"2024-06-26T12:09:59Z","abstract_excerpt":"Person-generic audio-driven face generation is a challenging task in computer vision. Previous methods have achieved remarkable progress in audio-visual synchronization, but there is still a significant gap between current results and practical applications. The challenges are two-fold: 1) Preserving unique individual traits for achieving high-precision lip synchronization. 2) Generating high-quality facial renderings in real-time performance. In this paper, we propose a novel generalized audio-driven framework RealTalk, which consists of an audio-to-expression transformer and a high-fidelity "},"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":"2406.18284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-26T12:09:59Z","cross_cats_sorted":[],"title_canon_sha256":"d3e04c843fd575839507754aa6ee0c8395e800c337381dcc04c43b3dccd0b5c8","abstract_canon_sha256":"9c0b97dfdb4a42022950c7cf575ce820a614544bb5cbf3806d72578f089a1249"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:23.578470Z","signature_b64":"Vyw8yl9DInGb5CtsZhyR2lc11/wxLgA1fiPP53tyETnfJeIU2QQL0xEWPFnrSVSfHQtJ+IoyxRueq7O6npBZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"094aa0010549aa3d24a06148542e373864dea7f557e1b59813face3ab6aff181","last_reissued_at":"2026-07-05T08:53:23.578004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:23.578004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RealTalk: Real-time and Realistic Audio-driven Face Generation with 3D Facial Prior-guided Identity Alignment Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Chuming Lin, Donghao Luo, Junwei Zhu, Xiaobin Hu, Xiaozhong Ji, Yanhao Ge, Ying Tai, Zhonggan Ding","submitted_at":"2024-06-26T12:09:59Z","abstract_excerpt":"Person-generic audio-driven face generation is a challenging task in computer vision. Previous methods have achieved remarkable progress in audio-visual synchronization, but there is still a significant gap between current results and practical applications. The challenges are two-fold: 1) Preserving unique individual traits for achieving high-precision lip synchronization. 2) Generating high-quality facial renderings in real-time performance. In this paper, we propose a novel generalized audio-driven framework RealTalk, which consists of an audio-to-expression transformer and a high-fidelity "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18284","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/2406.18284/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":"2406.18284","created_at":"2026-07-05T08:53:23.578080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18284v2","created_at":"2026-07-05T08:53:23.578080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18284","created_at":"2026-07-05T08:53:23.578080+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFFKAAIFJGVD","created_at":"2026-07-05T08:53:23.578080+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFFKAAIFJGVD2JFA","created_at":"2026-07-05T08:53:23.578080+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFFKAAIF","created_at":"2026-07-05T08:53:23.578080+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27779","citing_title":"MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BFFKAAIFJGVD2JFAMFEFILRXHB","json":"https://pith.science/pith/BFFKAAIFJGVD2JFAMFEFILRXHB.json","graph_json":"https://pith.science/api/pith-number/BFFKAAIFJGVD2JFAMFEFILRXHB/graph.json","events_json":"https://pith.science/api/pith-number/BFFKAAIFJGVD2JFAMFEFILRXHB/events.json","paper":"https://pith.science/paper/BFFKAAIF"},"agent_actions":{"view_html":"https://pith.science/pith/BFFKAAIFJGVD2JFAMFEFILRXHB","download_json":"https://pith.science/pith/BFFKAAIFJGVD2JFAMFEFILRXHB.json","view_paper":"https://pith.science/paper/BFFKAAIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18284&json=true","fetch_graph":"https://pith.science/api/pith-number/BFFKAAIFJGVD2JFAMFEFILRXHB/graph.json","fetch_events":"https://pith.science/api/pith-number/BFFKAAIFJGVD2JFAMFEFILRXHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFFKAAIFJGVD2JFAMFEFILRXHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFFKAAIFJGVD2JFAMFEFILRXHB/action/storage_attestation","attest_author":"https://pith.science/pith/BFFKAAIFJGVD2JFAMFEFILRXHB/action/author_attestation","sign_citation":"https://pith.science/pith/BFFKAAIFJGVD2JFAMFEFILRXHB/action/citation_signature","submit_replication":"https://pith.science/pith/BFFKAAIFJGVD2JFAMFEFILRXHB/action/replication_record"}},"created_at":"2026-07-05T08:53:23.578080+00:00","updated_at":"2026-07-05T08:53:23.578080+00:00"}