{"url":"/task/lip-sync","name":"Unconstrained Lip-synchronization","slug":"lip-sync","description_markdown":"Given a video of an arbitrary person, and an arbitrary driving speech, the task is to generate a lip-synced video that matches the given speech. \r\n\r\nThis task requires the approach to not be constrained by identity, voice, or language.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":4,"papers_with_code":4,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/lip-sync-on-lrs2","slug":"lip-sync-on-lrs2","dataset":"LRS2","dataset_url":"/dataset/lrs2","rows_in_archive":3,"metrics":["FID","LSE-D","LSE-C"],"first_row_in_archive_order":{"model":"Wav2Lip + ViT + MARLIN","paper_title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","paper_url":"/paper/marlin-masked-autoencoder-for-facial-video","paper_date":"2022-11-12","arxiv_id":"2211.06627","code_links":[{"title":"ControlNet/MARLIN","url":"https://github.com/ControlNet/MARLIN"}],"syntology":null}},{"leaderboard":"/sota/lip-sync-on-lrs3","slug":"lip-sync-on-lrs3","dataset":"LRS3","dataset_url":null,"rows_in_archive":2,"metrics":["FID","LSE-C","LSE-D"],"first_row_in_archive_order":{"model":"Wav2Lip + GAN","paper_title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","paper_url":"/paper/a-lip-sync-expert-is-all-you-need-for-speech","paper_date":"2020-08-23","arxiv_id":"2008.10010","code_links":[{"title":"Rudrabha/Wav2Lip","url":"https://github.com/Rudrabha/Wav2Lip"},{"title":"mowshon/lipsync","url":"https://github.com/mowshon/lipsync"},{"title":"PrashanthaTP/wav2mov","url":"https://github.com/PrashanthaTP/wav2mov"},{"title":"rockstar-0000/lip_sync_test","url":"https://github.com/rockstar-0000/lip_sync_test"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}}},{"leaderboard":"/sota/lip-sync-on-lrw","slug":"lip-sync-on-lrw","dataset":"LRW","dataset_url":"/dataset/lrw","rows_in_archive":2,"metrics":["FID","LSE-C","LSE-D"],"first_row_in_archive_order":{"model":"Wav2Lip + GAN","paper_title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","paper_url":"/paper/a-lip-sync-expert-is-all-you-need-for-speech","paper_date":"2020-08-23","arxiv_id":"2008.10010","code_links":[{"title":"Rudrabha/Wav2Lip","url":"https://github.com/Rudrabha/Wav2Lip"},{"title":"mowshon/lipsync","url":"https://github.com/mowshon/lipsync"},{"title":"PrashanthaTP/wav2mov","url":"https://github.com/PrashanthaTP/wav2mov"},{"title":"rockstar-0000/lip_sync_test","url":"https://github.com/rockstar-0000/lip_sync_test"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}}}],"datasets":[{"url":"/dataset/lrw","name":"LRW","full_name":"Lip Reading in the Wild","num_papers_in_archive":188},{"url":"/dataset/lrs2","name":"LRS2","full_name":"Lip Reading Sentences 2","num_papers_in_archive":115},{"url":"/dataset/glips","name":"GLips","full_name":"German Lips","num_papers_in_archive":6}],"subtasks":[],"parent_tasks":[{"url":"/task/talking-head-generation","name":"Talking Head Generation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":4,"of":4,"tagged_in_all":4,"items":[{"url":"/paper/a-lip-sync-expert-is-all-you-need-for-speech","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","date":"2020-08-23","arxiv_id":"2008.10010","repositories_listed":4,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/marlin-masked-autoencoder-for-facial-video","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","date":"2022-11-12","arxiv_id":"2211.06627","repositories_listed":1,"syntology":null},{"url":"/paper/towards-automatic-face-to-face-translation-1","title":"Towards Automatic Face-to-Face Translation","date":"2020-03-01","arxiv_id":"2003.00418","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/you-said-that","title":"You said that?","date":"2017-05-08","arxiv_id":"1705.02966","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}