{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WCEXBCHJQSR4LHP5QUTNTVJRWP","short_pith_number":"pith:WCEXBCHJ","schema_version":"1.0","canonical_sha256":"b0897088e984a3c59dfd8526d9d531b3cd6619bf9467791e4cdc7f69f953e027","source":{"kind":"arxiv","id":"2404.19040","version":1},"attestation_state":"computed","paper":{"title":"GSTalker: Real-time Audio-Driven Talking Face Generation via Deformable Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Chen, Chenpeng Du, Qi Chen, Ran Yi, Shoukang Hu, Xie Chen, Yanmin Qian","submitted_at":"2024-04-29T18:28:36Z","abstract_excerpt":"We present GStalker, a 3D audio-driven talking face generation model with Gaussian Splatting for both fast training (40 minutes) and real-time rendering (125 FPS) with a 3$\\sim$5 minute video for training material, in comparison with previous 2D and 3D NeRF-based modeling frameworks which require hours of training and seconds of rendering per frame. Specifically, GSTalker learns an audio-driven Gaussian deformation field to translate and transform 3D Gaussians to synchronize with audio information, in which multi-resolution hashing grid-based tri-plane and temporal smooth module are incorporat"},"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":"2404.19040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-29T18:28:36Z","cross_cats_sorted":[],"title_canon_sha256":"d16bf375ae24d0e5d39e08933171e13a9616f0c863b56c7a318674fc2f0a9986","abstract_canon_sha256":"2ae867eb8ebe34084dcbdc2ce9670dbe1ea2305eb86507853a15353160fc6631"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:36.668345Z","signature_b64":"cd5aEUNQ72ibaBUlVjcNma3puzzjnRiMR++Bn3nTFMQiXatL6dOoDcXsNlc9mwuI0CNSIaVlmdIz9ehxBmQaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0897088e984a3c59dfd8526d9d531b3cd6619bf9467791e4cdc7f69f953e027","last_reissued_at":"2026-07-05T08:13:36.667915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:36.667915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GSTalker: Real-time Audio-Driven Talking Face Generation via Deformable Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Chen, Chenpeng Du, Qi Chen, Ran Yi, Shoukang Hu, Xie Chen, Yanmin Qian","submitted_at":"2024-04-29T18:28:36Z","abstract_excerpt":"We present GStalker, a 3D audio-driven talking face generation model with Gaussian Splatting for both fast training (40 minutes) and real-time rendering (125 FPS) with a 3$\\sim$5 minute video for training material, in comparison with previous 2D and 3D NeRF-based modeling frameworks which require hours of training and seconds of rendering per frame. Specifically, GSTalker learns an audio-driven Gaussian deformation field to translate and transform 3D Gaussians to synchronize with audio information, in which multi-resolution hashing grid-based tri-plane and temporal smooth module are incorporat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19040","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/2404.19040/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":"2404.19040","created_at":"2026-07-05T08:13:36.667983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19040v1","created_at":"2026-07-05T08:13:36.667983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19040","created_at":"2026-07-05T08:13:36.667983+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCEXBCHJQSR4","created_at":"2026-07-05T08:13:36.667983+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCEXBCHJQSR4LHP5","created_at":"2026-07-05T08:13:36.667983+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCEXBCHJ","created_at":"2026-07-05T08:13:36.667983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23692","citing_title":"Personalizing Causal Audio-Driven Facial Motion via Dynamic Multi-modal Retrieval","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCEXBCHJQSR4LHP5QUTNTVJRWP","json":"https://pith.science/pith/WCEXBCHJQSR4LHP5QUTNTVJRWP.json","graph_json":"https://pith.science/api/pith-number/WCEXBCHJQSR4LHP5QUTNTVJRWP/graph.json","events_json":"https://pith.science/api/pith-number/WCEXBCHJQSR4LHP5QUTNTVJRWP/events.json","paper":"https://pith.science/paper/WCEXBCHJ"},"agent_actions":{"view_html":"https://pith.science/pith/WCEXBCHJQSR4LHP5QUTNTVJRWP","download_json":"https://pith.science/pith/WCEXBCHJQSR4LHP5QUTNTVJRWP.json","view_paper":"https://pith.science/paper/WCEXBCHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19040&json=true","fetch_graph":"https://pith.science/api/pith-number/WCEXBCHJQSR4LHP5QUTNTVJRWP/graph.json","fetch_events":"https://pith.science/api/pith-number/WCEXBCHJQSR4LHP5QUTNTVJRWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCEXBCHJQSR4LHP5QUTNTVJRWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCEXBCHJQSR4LHP5QUTNTVJRWP/action/storage_attestation","attest_author":"https://pith.science/pith/WCEXBCHJQSR4LHP5QUTNTVJRWP/action/author_attestation","sign_citation":"https://pith.science/pith/WCEXBCHJQSR4LHP5QUTNTVJRWP/action/citation_signature","submit_replication":"https://pith.science/pith/WCEXBCHJQSR4LHP5QUTNTVJRWP/action/replication_record"}},"created_at":"2026-07-05T08:13:36.667983+00:00","updated_at":"2026-07-05T08:13:36.667983+00:00"}