{"url":"/sota/motion-synthesis-on-aist","task":{"name":"Motion Synthesis","url":"/task/motion-synthesis","note":null},"dataset":{"name":"AIST++","url":"/dataset/aist"},"category":"Computer Vision","categories":["Computer Code","Computer Vision"],"category_note":null,"description":"Creating a video where people in the images move (such as blinking or smiling) requires specialized AI technology like Deepfake or Motion Synthesis, which I cannot do directly here.  \r\n\r\nHowever, if you want a video made from the images you provided, I can create an animated slideshow with cute effects and royalty-free background music. Would you be interested in this?","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["FID","Beat alignment score"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"FID":"lower","Beat alignment score":"higher"}},"counts":{"rows":12,"rows_with_code":9,"rows_with_paper_page":12,"rows_dated":12,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Motion Anything","metrics":{"Beat alignment score":"0.2757","FID":"17.22"},"uses_additional_data":false,"paper_date":"2025-03-10","paper":"/paper/motion-anything-any-to-motion-generation","paper_url":"https://arxiv.org/abs/2503.06955v1","paper_title":"Motion Anything: Any to Motion Generation","code":"https://github.com/steve-zeyu-zhang/MotionAnything","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"UDE","metrics":{"Beat alignment score":"0.2311","FID":"17.25"},"uses_additional_data":false,"paper_date":"2022-11-29","paper":"/paper/ude-a-unified-driving-engine-for-human-motion","paper_url":"https://arxiv.org/abs/2211.16016v1","paper_title":"UDE: A Unified Driving Engine for Human Motion Generation","code":"https://github.com/zixiangzhou916/ude","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"TM2D","metrics":{"Beat alignment score":"0.2049","FID":"19.01"},"uses_additional_data":false,"paper_date":"2023-04-05","paper":"/paper/tm2d-bimodality-driven-3d-dance-generation","paper_url":"https://arxiv.org/abs/2304.02419v2","paper_title":"TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration","code":"https://github.com/Garfield-kh/TM2D","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":4,"model":"TM2D (only motion data)","metrics":{"Beat alignment score":"0.2127","FID":"23.94"},"uses_additional_data":false,"paper_date":"2023-04-05","paper":"/paper/tm2d-bimodality-driven-3d-dance-generation","paper_url":"https://arxiv.org/abs/2304.02419v2","paper_title":"TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration","code":"https://github.com/Garfield-kh/TM2D","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":5,"model":"Bailando","metrics":{"Beat alignment score":"0.233","FID":"28.16"},"uses_additional_data":false,"paper_date":"2022-03-24","paper":"/paper/bailando-3d-dance-generation-by-actor-critic","paper_url":"https://arxiv.org/abs/2203.13055v2","paper_title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","code":"https://github.com/lisiyao21/bailando","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":6,"model":"AI Choreographer","metrics":{"Beat alignment score":"0.221","FID":"35.35"},"uses_additional_data":false,"paper_date":"2021-01-21","paper":"/paper/learn-to-dance-with-aist-music-conditioned-3d","paper_url":"https://arxiv.org/abs/2101.08779v3","paper_title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","code":"https://github.com/google-research/mint","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"Lodge (DDPM)","metrics":{"Beat alignment score":"0.24","FID":"37.09"},"uses_additional_data":false,"paper_date":"2024-03-15","paper":"/paper/lodge-a-coarse-to-fine-diffusion-network-for","paper_url":"https://arxiv.org/abs/2403.10518v3","paper_title":"Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives","code":"https://github.com/li-ronghui/LODGE","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":17}},{"rank_in_archive_order":8,"model":"MoFusion","metrics":{"Beat alignment score":"0.253","FID":"50.31"},"uses_additional_data":false,"paper_date":"2022-12-08","paper":"/paper/mofusion-a-framework-for-denoising-diffusion","paper_url":"https://arxiv.org/abs/2212.04495v2","paper_title":"MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"DanceNet","metrics":{"Beat alignment score":"0.143","FID":"69.13"},"uses_additional_data":false,"paper_date":"2020-02-02","paper":"/paper/music2dance-music-driven-dance-generation","paper_url":"https://arxiv.org/abs/2002.03761v2","paper_title":"Music2Dance: DanceNet for Music-driven Dance Generation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"Dance Revolution","metrics":{"Beat alignment score":"0.195","FID":"73.42"},"uses_additional_data":false,"paper_date":"2020-06-11","paper":"/paper/dance-revolution-long-sequence-dance","paper_url":"https://arxiv.org/abs/2006.06119v8","paper_title":"Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"EDGE (w=1)","metrics":{"Beat alignment score":"0.27"},"uses_additional_data":false,"paper_date":"2022-11-19","paper":"/paper/edge-editable-dance-generation-from-music","paper_url":"https://arxiv.org/abs/2211.10658v2","paper_title":"EDGE: Editable Dance Generation From Music","code":"https://github.com/Stanford-TML/EDGE","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"EDGE (w=2)","metrics":{"Beat alignment score":"0.26"},"uses_additional_data":false,"paper_date":"2022-11-19","paper":"/paper/edge-editable-dance-generation-from-music","paper_url":"https://arxiv.org/abs/2211.10658v2","paper_title":"EDGE: Editable Dance Generation From Music","code":"https://github.com/Stanford-TML/EDGE","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":6,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":22,"n_unverified":12,"n_samples":34,"n_pointer_only_licence":23,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":30,"n_unverified":16,"n_samples":46,"n_pointer_only_licence":24,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}