{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NFHYJS42ST2NTUCPUZOEWLJOEA","short_pith_number":"pith:NFHYJS42","schema_version":"1.0","canonical_sha256":"694f84cb9a94f4d9d04fa65c4b2d2e200e69030fa3eddad2fa4dd17e7654451b","source":{"kind":"arxiv","id":"2604.02941","version":2},"attestation_state":"computed","paper":{"title":"MMTalker: Multiresolution 3D Talking Head Synthesis with Multimodal Feature Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MMTalker synthesizes detailed 3D talking heads from speech by combining UV mesh parameterization with dual cross-attention fusion of audio and geometric features.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Liu, Bo Li, Zhifen He, Zhixiang Xiong","submitted_at":"2026-04-03T10:17:39Z","abstract_excerpt":"Speech-driven three-dimensional (3D) facial animation synthesis aims to build a mapping from one-dimensional (1D) speech signals to time-varying 3D facial motion signals. Current methods still face challenges in maintaining lip-sync accuracy and producing realistic facial expressions, primarily due to the highly ill-posed nature of this cross-modal mapping. In this paper, we introduce a novel 3D audio-driven facial animation synthesis method through multi-resolution representation and multi-modal feature fusion, called MMTalker which can accurately reconstruct the rich details of 3D facial mot"},"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":true},"canonical_record":{"source":{"id":"2604.02941","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-03T10:17:39Z","cross_cats_sorted":[],"title_canon_sha256":"ae428a3e486aa52d15511d0ca7e4b51e935db6a5bf027e5ec89dc779a6f94065","abstract_canon_sha256":"7ff1551469e95218086981257d5d647316731dc1b2b69fac3eb5fcd995f6d2b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:16.215718Z","signature_b64":"K/LkhcbibGpa6jK8sxVQGH0xblIalRmxqcUWrMHiQ77PUM6FeXrql4owOmaw2+4om4uzDhGXvdLdP+3uI+cUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"694f84cb9a94f4d9d04fa65c4b2d2e200e69030fa3eddad2fa4dd17e7654451b","last_reissued_at":"2026-06-02T01:04:16.215262Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:16.215262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMTalker: Multiresolution 3D Talking Head Synthesis with Multimodal Feature Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MMTalker synthesizes detailed 3D talking heads from speech by combining UV mesh parameterization with dual cross-attention fusion of audio and geometric features.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Liu, Bo Li, Zhifen He, Zhixiang Xiong","submitted_at":"2026-04-03T10:17:39Z","abstract_excerpt":"Speech-driven three-dimensional (3D) facial animation synthesis aims to build a mapping from one-dimensional (1D) speech signals to time-varying 3D facial motion signals. Current methods still face challenges in maintaining lip-sync accuracy and producing realistic facial expressions, primarily due to the highly ill-posed nature of this cross-modal mapping. In this paper, we introduce a novel 3D audio-driven facial animation synthesis method through multi-resolution representation and multi-modal feature fusion, called MMTalker which can accurately reconstruct the rich details of 3D facial mot"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MMTalker can accurately reconstruct the rich details of 3D facial motion and achieves significant improvements over state-of-the-art methods, especially in the synchronization accuracy of lip and eye movements.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the combination of non-uniform differentiable sampling on UV-parameterized meshes and dual cross-attention fusion will resolve the ill-posed speech-to-3D-motion mapping without introducing artifacts or requiring extensive post-processing.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MMTalker combines multi-resolution mesh sampling with residual graph convolutions and dual cross-attention to synthesize accurate 3D talking head motions from audio.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MMTalker synthesizes detailed 3D talking heads from speech by combining UV mesh parameterization with dual cross-attention fusion of audio and geometric features.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e09bc56e81fcaa308190a6a89eda3f0593c4cbce5554b00468c6d6c22b1cb547"},"source":{"id":"2604.02941","kind":"arxiv","version":2},"verdict":{"id":"c5d10b79-6e4a-48c7-914d-712d63bd7642","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T19:43:00.793617Z","strongest_claim":"MMTalker can accurately reconstruct the rich details of 3D facial motion and achieves significant improvements over state-of-the-art methods, especially in the synchronization accuracy of lip and eye movements.","one_line_summary":"MMTalker combines multi-resolution mesh sampling with residual graph convolutions and dual cross-attention to synthesize accurate 3D talking head motions from audio.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the combination of non-uniform differentiable sampling on UV-parameterized meshes and dual cross-attention fusion will resolve the ill-posed speech-to-3D-motion mapping without introducing artifacts or requiring extensive post-processing.","pith_extraction_headline":"MMTalker synthesizes detailed 3D talking heads from speech by combining UV mesh parameterization with dual cross-attention fusion of audio and geometric features."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.02941/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":1,"snapshot_sha256":"6eb294c43f91bdebe296fcf460f86187f20249dfa51e514bb98296680b13ae4d"},"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":"2604.02941","created_at":"2026-06-02T01:04:16.215321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.02941v2","created_at":"2026-06-02T01:04:16.215321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.02941","created_at":"2026-06-02T01:04:16.215321+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFHYJS42ST2N","created_at":"2026-06-02T01:04:16.215321+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFHYJS42ST2NTUCP","created_at":"2026-06-02T01:04:16.215321+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFHYJS42","created_at":"2026-06-02T01:04:16.215321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFHYJS42ST2NTUCPUZOEWLJOEA","json":"https://pith.science/pith/NFHYJS42ST2NTUCPUZOEWLJOEA.json","graph_json":"https://pith.science/api/pith-number/NFHYJS42ST2NTUCPUZOEWLJOEA/graph.json","events_json":"https://pith.science/api/pith-number/NFHYJS42ST2NTUCPUZOEWLJOEA/events.json","paper":"https://pith.science/paper/NFHYJS42"},"agent_actions":{"view_html":"https://pith.science/pith/NFHYJS42ST2NTUCPUZOEWLJOEA","download_json":"https://pith.science/pith/NFHYJS42ST2NTUCPUZOEWLJOEA.json","view_paper":"https://pith.science/paper/NFHYJS42","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.02941&json=true","fetch_graph":"https://pith.science/api/pith-number/NFHYJS42ST2NTUCPUZOEWLJOEA/graph.json","fetch_events":"https://pith.science/api/pith-number/NFHYJS42ST2NTUCPUZOEWLJOEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFHYJS42ST2NTUCPUZOEWLJOEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFHYJS42ST2NTUCPUZOEWLJOEA/action/storage_attestation","attest_author":"https://pith.science/pith/NFHYJS42ST2NTUCPUZOEWLJOEA/action/author_attestation","sign_citation":"https://pith.science/pith/NFHYJS42ST2NTUCPUZOEWLJOEA/action/citation_signature","submit_replication":"https://pith.science/pith/NFHYJS42ST2NTUCPUZOEWLJOEA/action/replication_record"}},"created_at":"2026-06-02T01:04:16.215321+00:00","updated_at":"2026-06-02T01:04:16.215321+00:00"}