{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FGSFKX3VX5O2XJAD6Q3C22B6QV","short_pith_number":"pith:FGSFKX3V","schema_version":"1.0","canonical_sha256":"29a4555f75bf5daba403f4362d683e857df378a1e9a34f232014fc42229d42a3","source":{"kind":"arxiv","id":"2501.01798","version":1},"attestation_state":"computed","paper":{"title":"JoyGen: Audio-Driven 3D Depth-Aware Talking-Face Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dajiang Wu, Jun Lv, Junshi Huang, Qili Wang, Zihang Xu","submitted_at":"2025-01-03T13:14:52Z","abstract_excerpt":"Significant progress has been made in talking-face video generation research; however, precise lip-audio synchronization and high visual quality remain challenging in editing lip shapes based on input audio. This paper introduces JoyGen, a novel two-stage framework for talking-face generation, comprising audio-driven lip motion generation and visual appearance synthesis. In the first stage, a 3D reconstruction model and an audio2motion model predict identity and expression coefficients respectively. Next, by integrating audio features with a facial depth map, we provide comprehensive supervisi"},"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":"2501.01798","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T13:14:52Z","cross_cats_sorted":[],"title_canon_sha256":"dfbe48c9085e36a33341b87beae0e1c99acd7b4fa2c2a6b4fbcd076ff3d0bccc","abstract_canon_sha256":"38ec06538e8deec930fe7e334c29e4a2e4fbf900755c9f13262aa6e2cfd292f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:41.136421Z","signature_b64":"T9EktBFJ89WUXKKy2StgwG/SRxcUn/LJwgpiS5Q26rZ156PKyhMPfsiGWCUJqyy9+NKxK96qj1wWw2nGfgRiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29a4555f75bf5daba403f4362d683e857df378a1e9a34f232014fc42229d42a3","last_reissued_at":"2026-07-05T09:56:41.135966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:41.135966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JoyGen: Audio-Driven 3D Depth-Aware Talking-Face Video Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dajiang Wu, Jun Lv, Junshi Huang, Qili Wang, Zihang Xu","submitted_at":"2025-01-03T13:14:52Z","abstract_excerpt":"Significant progress has been made in talking-face video generation research; however, precise lip-audio synchronization and high visual quality remain challenging in editing lip shapes based on input audio. This paper introduces JoyGen, a novel two-stage framework for talking-face generation, comprising audio-driven lip motion generation and visual appearance synthesis. In the first stage, a 3D reconstruction model and an audio2motion model predict identity and expression coefficients respectively. Next, by integrating audio features with a facial depth map, we provide comprehensive supervisi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01798","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/2501.01798/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":"2501.01798","created_at":"2026-07-05T09:56:41.136025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01798v1","created_at":"2026-07-05T09:56:41.136025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01798","created_at":"2026-07-05T09:56:41.136025+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGSFKX3VX5O2","created_at":"2026-07-05T09:56:41.136025+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGSFKX3VX5O2XJAD","created_at":"2026-07-05T09:56:41.136025+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGSFKX3V","created_at":"2026-07-05T09:56:41.136025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20452","citing_title":"JOLT3D: Joint Learning of Talking Heads and 3DMM Parameters with Application to Lip-Sync","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV","json":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV.json","graph_json":"https://pith.science/api/pith-number/FGSFKX3VX5O2XJAD6Q3C22B6QV/graph.json","events_json":"https://pith.science/api/pith-number/FGSFKX3VX5O2XJAD6Q3C22B6QV/events.json","paper":"https://pith.science/paper/FGSFKX3V"},"agent_actions":{"view_html":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV","download_json":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV.json","view_paper":"https://pith.science/paper/FGSFKX3V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01798&json=true","fetch_graph":"https://pith.science/api/pith-number/FGSFKX3VX5O2XJAD6Q3C22B6QV/graph.json","fetch_events":"https://pith.science/api/pith-number/FGSFKX3VX5O2XJAD6Q3C22B6QV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV/action/storage_attestation","attest_author":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV/action/author_attestation","sign_citation":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV/action/citation_signature","submit_replication":"https://pith.science/pith/FGSFKX3VX5O2XJAD6Q3C22B6QV/action/replication_record"}},"created_at":"2026-07-05T09:56:41.136025+00:00","updated_at":"2026-07-05T09:56:41.136025+00:00"}