{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/musetalk-real-time-high-quality-lip","title":"MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling","arxiv_id":"2410.10122","date":"2024-10-14","proceeding":null,"authors":["Yue Zhang","Zhizhou Zhong","Minhao Liu","Zhaokang Chen","Bin Wu","Yubin Zeng","Chao Zhan","Yingjie He","Junxin Huang","Wenjiang Zhou"],"abstract":"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 Pretraining stage, we propose Informative Frame Sampling to temporally align reference-source pose pairs, eliminating redundant feature interference while preserving identity cues. (2) In the Lip-Sync Adversarial Finetuning stage, we employ Dynamic Margin Sampling to spatially select the most suitable lip-movement-promoting regions, balancing audio-visual synchronization and dental clarity. (3) MuseTalk establishes an effective audio-visual feature fusion framework in the latent space, delivering 30 FPS output at 256*256 resolution on an NVIDIA V100 GPU. Extensive experiments demonstrate that MuseTalk outperforms state-of-the-art methods in visual fidelity while achieving comparable lip-sync accuracy. %The codes and models will be made publicly available upon acceptance. The code is made available at \\href{https://github.com/TMElyralab/MuseTalk}{https://github.com/TMElyralab/MuseTalk}","url_abs":"https://arxiv.org/abs/2410.10122v3","url_pdf":"https://arxiv.org/pdf/2410.10122v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"musetalk-real-time-high-quality-lip","repo_url":"https://github.com/tmelyralab/musetalk","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"audio-visual-synchronization","task_name":"Audio-Visual Synchronization"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.10122","atlas_url":"https://app.syntology.ai/?focus=2410.10122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10122"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tmelyralab/musetalk","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":1,"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":8,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"tmelyralab/musetalk","repo_kind":"official","path":"musetalk/loss/resnet.py","file_url":"https://github.com/tmelyralab/musetalk/blob/HEAD/musetalk/loss/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"9fd8f5e1bf80ffb7","entry":"cosine_loss","repo":"tmelyralab/musetalk","repo_kind":"official","path":"musetalk/loss/syncnet.py","file_url":"https://github.com/tmelyralab/musetalk/blob/HEAD/musetalk/loss/syncnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9fd8f5e1bf80ffb7"}},{"code_sha256_prefix":"8ea8aee80bdd7940","entry":"face_seg","repo":"tmelyralab/musetalk","repo_kind":"official","path":"musetalk/utils/blending.py","file_url":"https://github.com/tmelyralab/musetalk/blob/HEAD/musetalk/utils/blending.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8ea8aee80bdd7940"}},{"code_sha256_prefix":"26b08d0f39a7f8a9","entry":"get_crop_box","repo":"tmelyralab/musetalk","repo_kind":"official","path":"musetalk/utils/blending.py","file_url":"https://github.com/tmelyralab/musetalk/blob/HEAD/musetalk/utils/blending.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"26b08d0f39a7f8a9"}},{"code_sha256_prefix":"ee234e9bbf144430","entry":"get_image","repo":"tmelyralab/musetalk","repo_kind":"official","path":"musetalk/utils/blending.py","file_url":"https://github.com/tmelyralab/musetalk/blob/HEAD/musetalk/utils/blending.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ee234e9bbf144430"}},{"code_sha256_prefix":"4097fa82487d0ec7","entry":"get_sync_loss","repo":"tmelyralab/musetalk","repo_kind":"official","path":"musetalk/loss/syncnet.py","file_url":"https://github.com/tmelyralab/musetalk/blob/HEAD/musetalk/loss/syncnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4097fa82487d0ec7"}},{"code_sha256_prefix":"64a588801da98180","entry":"vggface","repo":"tmelyralab/musetalk","repo_kind":"official","path":"musetalk/loss/vgg_face.py","file_url":"https://github.com/tmelyralab/musetalk/blob/HEAD/musetalk/loss/vgg_face.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"64a588801da98180"}},{"code_sha256_prefix":"e9ff5e19987cb4f7","entry":"ensure_wav","repo":"tmelyralab/musetalk","repo_kind":"official","path":"musetalk/utils/audio_utils.py","file_url":"https://github.com/tmelyralab/musetalk/blob/HEAD/musetalk/utils/audio_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e9ff5e19987cb4f7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}