{"url":"/dataset/lafan1","name":"LaFAN1","full_name":"Ubisoft La Forge Animation Dataset","description_markdown":"# Ubisoft La Forge Animation Dataset (\"LAFAN1\")\r\n\r\nUbisoft La Forge Animation dataset and accompanying code for the SIGGRAPH 2020 paper [Robust Motion In-betweening](https://montreal.ubisoft.com/en/automatic-in-betweening-for-faster-animation-authoring/).\r\n\r\nShot in May 2017.\r\n\r\nThis dataset can be used under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Public License (see license.txt).\r\n\r\nIf you use this dataset or transition benchmarking code, please consider citing the paper:\r\n```\r\n@article{harvey2020robust,\r\nauthor    = {Félix G. Harvey and Mike Yurick and Derek Nowrouzezahrai and Christopher Pal},\r\ntitle     = {Robust Motion In-Betweening},\r\nbooktitle = {ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH)},\r\npublisher = {ACM},\r\nvolume    = {39},\r\nnumber    = {4},\r\nyear      = {2020}\r\n}\r\n```\r\n\r\nYou may also want to consider the following papers, as they also use this dataset (or parts of it):\r\n\r\n* [Learned Motion Matching (Holden et al., 2020)](http://theorangeduck.com/media/uploads/other_stuff/Learned_Motion_Matching.pdf)\r\n\r\n* [Subspace Neural Physics: Fast Data-Driven Interactive Simulation (Holden et al., 2019)](http://www.theorangeduck.com/media/uploads/other_stuff/deep-cloth-paper.pdf)\r\n\r\n* [DReCon: Data-Driven Responsive Control of Physics-Based Characters (Bergamin et al., 2019)](https://static-wordpress.akamaized.net/montreal.ubisoft.com/wp-content/uploads/2019/11/13214229/DReCon.pdf)\r\n\r\n* [Robust Solving of Optical Motion Capture Data by Denoising (Holden, 2018)](http://theorangeduck.com/media/uploads/other_stuff/neural_solver.pdf)\r\n\r\n* [Recurrent Transition Networks for Character Locomotion (Harvey et al., 2018)](https://arxiv.org/pdf/1810.02363.pdf)\r\n\r\n## Data\r\nThe animation data is contained in the lafan1.zip file.  \r\nAll the animation sequences are in the BVH file format.  \r\nThere are 5 subjects in the dataset, 77 sequences, and 496,672 motion frames at 30fps (~4.6 hours).  \r\nEvery BVH file is named with the following convention: \\[*theme*\\]\\[*take number*\\]_\\[*subject ID*\\].bvh.  \r\nAny sequences sharing the same *theme* and *take_number* were recorded at the same time in the studio.  \r\nThemes are high level indicators of the actions in the sequences.\r\n\r\nThe following themes are present in the LaFAN1 dataset:\r\n\r\n|   Theme         |  Description                                  |Number of sequences|\r\n|:----------------|:------------------------------------------    |:-----------------:|\r\n| Obstacles       |  Locomotion on uneven terrain                 |17                 |\r\n| Walk            |  Walking locomotion, with different styles    |12                 |\r\n| Dance           |  Free dancing                                 |8                  |\r\n| Fall and get up |  Falling on the ground and getting back up    |6                  |\r\n| Aiming          |  Locomotion while handling or aiming a gun    |5                  |\r\n| Ground          |  Locomotion while crawling and crouching      |5                  |\r\n| Multiple actions|  Miscellaneous/multiple movements per sequence|4                  |\r\n| Run             |  Jogging/Running locomotion                   |4                  |\r\n| Fight           |  Various fight movements                      |3                  |\r\n| Jumps           |  Locomotion with one and two-leg jumps        |3                  |\r\n| Fight and sports|  Fight and sports movements                   |2                  |\r\n| Push and stumble|  Pushing, stumbling and recovery              |3                  |\r\n| Push and fall   |  Pushing, falling, and getting up             |2                  |\r\n| Sprint          |  Sprinting locomotion                         |2                  |\r\n| Push            |  Pushing adversary                            |1                  |\r\n\r\n\r\n© [2018] Ubisoft Entertainment. All Rights Reserved","description_withheld":null,"homepage":"https://github.com/ubisoft/ubisoft-laforge-animation-dataset","introduced_date":"2020-07-01","introduced_date_note":null,"introduced_by":null,"license":{"name":"Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Public License","url":"https://github.com/ubisoft/ubisoft-laforge-animation-dataset/blob/master/license.txt"},"modalities":[{"name":"3D","url":"/datasets/modality/3d"}],"tasks":[{"name":"Motion Synthesis","url":"/task/motion-synthesis","datasets_with_task":"/datasets/task/motion-synthesis"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["LaFAN1"],"data_loaders":[],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/motion-synthesis-on-lafan1","task":"Motion Synthesis","dataset_variant":"LaFAN1","rows":4,"metrics":["L2Q@5","L2Q@15","L2Q@30","L2P@5","L2P@15","L2P@30","NPSS@5","NPSS@15","NPSS@30"],"first_row_in_archive_order":{"model":"$\\Delta$-interpolator","paper":"/paper/motion-inbetweening-via-deep-d-interpolator","metrics":{"L2P@15":"0.47","L2P@30":"1.00","L2P@5":"0.13","L2Q@15":"0.32","L2Q@30":"0.57","L2Q@5":"0.11","NPSS@15":"0.0217","NPSS@30":"0.1217","NPSS@5":"0.0014"},"code_links":[{"title":"boreshkinai/delta-interpolator","url":"https://github.com/boreshkinai/delta-interpolator"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/motion-inbetweening-via-deep-d-interpolator","title":"Motion Inbetweening via Deep $Δ$-Interpolator","date":"2022-01-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/task-generic-hierarchical-human-motion-prior","title":"Task-Generic Hierarchical Human Motion Prior using VAEs","date":"2021-06-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/single-shot-motion-completion-with","title":"Single-Shot Motion Completion with Transformer","date":"2021-03-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/robust-motion-in-betweening","title":"Robust Motion In-betweening","date":"2021-02-09","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}