{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NACEVQ7I6ZXE43KQ75VIG7LI6O","short_pith_number":"pith:NACEVQ7I","schema_version":"1.0","canonical_sha256":"68044ac3e8f66e4e6d50ff6a837d68f3b542a9d82459f9b202d6271de8d5efc4","source":{"kind":"arxiv","id":"2404.16012","version":2},"attestation_state":"computed","paper":{"title":"GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Heeji Yoon, Jaehoon Ko, JoungBin Lee, Kyusun Cho, Sangjun Ahn, Seungryong Kim, Yeobin Hong","submitted_at":"2024-04-24T17:45:24Z","abstract_excerpt":"We propose GaussianTalker, a novel framework for real-time generation of pose-controllable talking heads. It leverages the fast rendering capabilities of 3D Gaussian Splatting (3DGS) while addressing the challenges of directly controlling 3DGS with speech audio. GaussianTalker constructs a canonical 3DGS representation of the head and deforms it in sync with the audio. A key insight is to encode the 3D Gaussian attributes into a shared implicit feature representation, where it is merged with audio features to manipulate each Gaussian attribute. This design exploits the spatial-aware features a"},"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":"2404.16012","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T17:45:24Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"09792e656e30bf0d5dc471059e9e9afedfee406d34e47409431bd525a542a360","abstract_canon_sha256":"ff0f9e897b4bde67fde1c3c4a2a3bd7b2f8a6a0feee86a00695ec720b9c178f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:00.161761Z","signature_b64":"NLMbauIKPw9Gi59sPht332m1fhNO9QzdF/Xpb7fJbrhi6n1ZGufdoLywx7fFr+VqQInzWo8sPNHNJBvIshUfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68044ac3e8f66e4e6d50ff6a837d68f3b542a9d82459f9b202d6271de8d5efc4","last_reissued_at":"2026-07-05T08:12:00.161328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:00.161328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Heeji Yoon, Jaehoon Ko, JoungBin Lee, Kyusun Cho, Sangjun Ahn, Seungryong Kim, Yeobin Hong","submitted_at":"2024-04-24T17:45:24Z","abstract_excerpt":"We propose GaussianTalker, a novel framework for real-time generation of pose-controllable talking heads. It leverages the fast rendering capabilities of 3D Gaussian Splatting (3DGS) while addressing the challenges of directly controlling 3DGS with speech audio. GaussianTalker constructs a canonical 3DGS representation of the head and deforms it in sync with the audio. A key insight is to encode the 3D Gaussian attributes into a shared implicit feature representation, where it is merged with audio features to manipulate each Gaussian attribute. This design exploits the spatial-aware features a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16012","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/2404.16012/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":"2404.16012","created_at":"2026-07-05T08:12:00.161386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16012v2","created_at":"2026-07-05T08:12:00.161386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16012","created_at":"2026-07-05T08:12:00.161386+00:00"},{"alias_kind":"pith_short_12","alias_value":"NACEVQ7I6ZXE","created_at":"2026-07-05T08:12:00.161386+00:00"},{"alias_kind":"pith_short_16","alias_value":"NACEVQ7I6ZXE43KQ","created_at":"2026-07-05T08:12:00.161386+00:00"},{"alias_kind":"pith_short_8","alias_value":"NACEVQ7I","created_at":"2026-07-05T08:12:00.161386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22678","citing_title":"RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22678","citing_title":"RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09956","citing_title":"SDTalk: Structured Facial Priors and Dual-Branch Motion Fields for Generalizable Gaussian Talking Head Synthesis","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NACEVQ7I6ZXE43KQ75VIG7LI6O","json":"https://pith.science/pith/NACEVQ7I6ZXE43KQ75VIG7LI6O.json","graph_json":"https://pith.science/api/pith-number/NACEVQ7I6ZXE43KQ75VIG7LI6O/graph.json","events_json":"https://pith.science/api/pith-number/NACEVQ7I6ZXE43KQ75VIG7LI6O/events.json","paper":"https://pith.science/paper/NACEVQ7I"},"agent_actions":{"view_html":"https://pith.science/pith/NACEVQ7I6ZXE43KQ75VIG7LI6O","download_json":"https://pith.science/pith/NACEVQ7I6ZXE43KQ75VIG7LI6O.json","view_paper":"https://pith.science/paper/NACEVQ7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16012&json=true","fetch_graph":"https://pith.science/api/pith-number/NACEVQ7I6ZXE43KQ75VIG7LI6O/graph.json","fetch_events":"https://pith.science/api/pith-number/NACEVQ7I6ZXE43KQ75VIG7LI6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NACEVQ7I6ZXE43KQ75VIG7LI6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NACEVQ7I6ZXE43KQ75VIG7LI6O/action/storage_attestation","attest_author":"https://pith.science/pith/NACEVQ7I6ZXE43KQ75VIG7LI6O/action/author_attestation","sign_citation":"https://pith.science/pith/NACEVQ7I6ZXE43KQ75VIG7LI6O/action/citation_signature","submit_replication":"https://pith.science/pith/NACEVQ7I6ZXE43KQ75VIG7LI6O/action/replication_record"}},"created_at":"2026-07-05T08:12:00.161386+00:00","updated_at":"2026-07-05T08:12:00.161386+00:00"}