{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U7E6GFOLUEIB4VG4ULN447HQ3X","short_pith_number":"pith:U7E6GFOL","schema_version":"1.0","canonical_sha256":"a7c9e315cba1101e54dca2dbce7cf0dddcac3914ca78f524bc6dab8f0e932e72","source":{"kind":"arxiv","id":"2309.07509","version":1},"attestation_state":"computed","paper":{"title":"DiffTalker: Co-driven audio-image diffusion for talking faces via intermediate landmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianzong Wang, Jing Xiao, Ning Cheng, Xulong Zhang, Zipeng Qi","submitted_at":"2023-09-14T08:22:34Z","abstract_excerpt":"Generating realistic talking faces is a complex and widely discussed task with numerous applications. In this paper, we present DiffTalker, a novel model designed to generate lifelike talking faces through audio and landmark co-driving. DiffTalker addresses the challenges associated with directly applying diffusion models to audio control, which are traditionally trained on text-image pairs. DiffTalker consists of two agent networks: a transformer-based landmarks completion network for geometric accuracy and a diffusion-based face generation network for texture details. Landmarks play a pivota"},"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":"2309.07509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-14T08:22:34Z","cross_cats_sorted":[],"title_canon_sha256":"122927b1f062c0f2c634e52866d4e7a76746b15e42a33511730ea1440e8bc3a6","abstract_canon_sha256":"cc14009c14f5f8f9747a880d8d3440fb58e21d49ff1f6268c16ddb55cbb97952"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:44.057435Z","signature_b64":"3f8r+PCtaHb4EgBDM1umrVIDrN0PnaSXGwbi2dXmDVTvBAn+L8n04/XY3TrRUzT0e8IES94pEm9jZU9/ytMHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7c9e315cba1101e54dca2dbce7cf0dddcac3914ca78f524bc6dab8f0e932e72","last_reissued_at":"2026-07-05T06:50:44.057002Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:44.057002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffTalker: Co-driven audio-image diffusion for talking faces via intermediate landmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianzong Wang, Jing Xiao, Ning Cheng, Xulong Zhang, Zipeng Qi","submitted_at":"2023-09-14T08:22:34Z","abstract_excerpt":"Generating realistic talking faces is a complex and widely discussed task with numerous applications. In this paper, we present DiffTalker, a novel model designed to generate lifelike talking faces through audio and landmark co-driving. DiffTalker addresses the challenges associated with directly applying diffusion models to audio control, which are traditionally trained on text-image pairs. DiffTalker consists of two agent networks: a transformer-based landmarks completion network for geometric accuracy and a diffusion-based face generation network for texture details. Landmarks play a pivota"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07509","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/2309.07509/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":"2309.07509","created_at":"2026-07-05T06:50:44.057063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07509v1","created_at":"2026-07-05T06:50:44.057063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07509","created_at":"2026-07-05T06:50:44.057063+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7E6GFOLUEIB","created_at":"2026-07-05T06:50:44.057063+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7E6GFOLUEIB4VG4","created_at":"2026-07-05T06:50:44.057063+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7E6GFOL","created_at":"2026-07-05T06:50:44.057063+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12594","citing_title":"A Simple and Efficient Baseline for Zero-Shot Generative Classification","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7E6GFOLUEIB4VG4ULN447HQ3X","json":"https://pith.science/pith/U7E6GFOLUEIB4VG4ULN447HQ3X.json","graph_json":"https://pith.science/api/pith-number/U7E6GFOLUEIB4VG4ULN447HQ3X/graph.json","events_json":"https://pith.science/api/pith-number/U7E6GFOLUEIB4VG4ULN447HQ3X/events.json","paper":"https://pith.science/paper/U7E6GFOL"},"agent_actions":{"view_html":"https://pith.science/pith/U7E6GFOLUEIB4VG4ULN447HQ3X","download_json":"https://pith.science/pith/U7E6GFOLUEIB4VG4ULN447HQ3X.json","view_paper":"https://pith.science/paper/U7E6GFOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07509&json=true","fetch_graph":"https://pith.science/api/pith-number/U7E6GFOLUEIB4VG4ULN447HQ3X/graph.json","fetch_events":"https://pith.science/api/pith-number/U7E6GFOLUEIB4VG4ULN447HQ3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7E6GFOLUEIB4VG4ULN447HQ3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7E6GFOLUEIB4VG4ULN447HQ3X/action/storage_attestation","attest_author":"https://pith.science/pith/U7E6GFOLUEIB4VG4ULN447HQ3X/action/author_attestation","sign_citation":"https://pith.science/pith/U7E6GFOLUEIB4VG4ULN447HQ3X/action/citation_signature","submit_replication":"https://pith.science/pith/U7E6GFOLUEIB4VG4ULN447HQ3X/action/replication_record"}},"created_at":"2026-07-05T06:50:44.057063+00:00","updated_at":"2026-07-05T06:50:44.057063+00:00"}