{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QDOUVJUNQWU24BCM7KN3GKBEWC","short_pith_number":"pith:QDOUVJUN","schema_version":"1.0","canonical_sha256":"80dd4aa68d85a9ae044cfa9bb32824b09701a2e2c78ce6059e0c097bb2e98664","source":{"kind":"arxiv","id":"2410.10122","version":3},"attestation_state":"computed","paper":{"title":"MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wu, Chao Zhan, Junxin Huang, Minhao Liu, Wenjiang Zhou, Yingjie He, Yubin Zeng, Yue Zhang, Zhaokang Chen, Zhizhou Zhong","submitted_at":"2024-10-14T03:22:26Z","abstract_excerpt":"Real-time video dubbing that preserves identity consistency while achieving accurate lip synchronization remains a critical challenge. Existing approaches face a trilemma: diffusion-based methods achieve high visual fidelity but suffer from prohibitive computational costs, while GAN-based solutions sacrifice lip-sync accuracy or dental details for real-time performance. We present MuseTalk, a novel two-stage training framework that resolves this trade-off through latent space optimization and spatio-temporal data sampling strategy. Our key innovations include: (1) During the Facial Abstract Pr"},"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":"2410.10122","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T03:22:26Z","cross_cats_sorted":[],"title_canon_sha256":"ca1367f1260bcbf2143125101d25fe7abe113eb705c38b171be4c52522ff3b84","abstract_canon_sha256":"4ce1dfb183b2012d89e6b0a977978c2dccccb950514d9aeca121479df20d47b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:21.736800Z","signature_b64":"NCealFRatbHApfsDLk83ieMA/poARr/xdZPg40ncZw7at45D6vYn4YdSLoT+KOiUk50yjXA9lqVnfAfzXTuXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80dd4aa68d85a9ae044cfa9bb32824b09701a2e2c78ce6059e0c097bb2e98664","last_reissued_at":"2026-07-05T10:39:21.736299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:21.736299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wu, Chao Zhan, Junxin Huang, Minhao Liu, Wenjiang Zhou, Yingjie He, Yubin Zeng, Yue Zhang, Zhaokang Chen, Zhizhou Zhong","submitted_at":"2024-10-14T03:22:26Z","abstract_excerpt":"Real-time video dubbing that preserves identity consistency while achieving accurate lip synchronization remains a critical challenge. Existing approaches face a trilemma: diffusion-based methods achieve high visual fidelity but suffer from prohibitive computational costs, while GAN-based solutions sacrifice lip-sync accuracy or dental details for real-time performance. We present MuseTalk, a novel two-stage training framework that resolves this trade-off through latent space optimization and spatio-temporal data sampling strategy. Our key innovations include: (1) During the Facial Abstract Pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10122","kind":"arxiv","version":3},"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/2410.10122/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":"2410.10122","created_at":"2026-07-05T10:39:21.736364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10122v3","created_at":"2026-07-05T10:39:21.736364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10122","created_at":"2026-07-05T10:39:21.736364+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDOUVJUNQWU2","created_at":"2026-07-05T10:39:21.736364+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDOUVJUNQWU24BCM","created_at":"2026-07-05T10:39:21.736364+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDOUVJUN","created_at":"2026-07-05T10:39:21.736364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11180","citing_title":"Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28568","citing_title":"KM-Speaker: Keypoint-Based Style Control for High-Quality Speech-Driven 3D Facial Animation and Dialogue Localization","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27779","citing_title":"MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16366","citing_title":"Fre-Res: Frequency-Residual Video Token Compression for Efficient Video MLLMs","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16918","citing_title":"HighSync: High-Quality Lip Synchronization via Latent Diffusion Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12052","citing_title":"FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23632","citing_title":"Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23325","citing_title":"EAD-Net: Emotion-Aware Talking Head Generation with Spatial Refinement and Temporal Coherence","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QDOUVJUNQWU24BCM7KN3GKBEWC","json":"https://pith.science/pith/QDOUVJUNQWU24BCM7KN3GKBEWC.json","graph_json":"https://pith.science/api/pith-number/QDOUVJUNQWU24BCM7KN3GKBEWC/graph.json","events_json":"https://pith.science/api/pith-number/QDOUVJUNQWU24BCM7KN3GKBEWC/events.json","paper":"https://pith.science/paper/QDOUVJUN"},"agent_actions":{"view_html":"https://pith.science/pith/QDOUVJUNQWU24BCM7KN3GKBEWC","download_json":"https://pith.science/pith/QDOUVJUNQWU24BCM7KN3GKBEWC.json","view_paper":"https://pith.science/paper/QDOUVJUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10122&json=true","fetch_graph":"https://pith.science/api/pith-number/QDOUVJUNQWU24BCM7KN3GKBEWC/graph.json","fetch_events":"https://pith.science/api/pith-number/QDOUVJUNQWU24BCM7KN3GKBEWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDOUVJUNQWU24BCM7KN3GKBEWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDOUVJUNQWU24BCM7KN3GKBEWC/action/storage_attestation","attest_author":"https://pith.science/pith/QDOUVJUNQWU24BCM7KN3GKBEWC/action/author_attestation","sign_citation":"https://pith.science/pith/QDOUVJUNQWU24BCM7KN3GKBEWC/action/citation_signature","submit_replication":"https://pith.science/pith/QDOUVJUNQWU24BCM7KN3GKBEWC/action/replication_record"}},"created_at":"2026-07-05T10:39:21.736364+00:00","updated_at":"2026-07-05T10:39:21.736364+00:00"}