{"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/motion-anything-any-to-motion-generation","title":"Motion Anything: Any to Motion Generation","arxiv_id":"2503.06955","date":"2025-03-10","proceeding":null,"authors":["Zeyu Zhang","Yiran Wang","Wei Mao","Danning Li","Rui Zhao","Biao Wu","Zirui Song","Bohan Zhuang","Ian Reid","Richard Hartley"],"abstract":"Conditional motion generation has been extensively studied in computer vision, yet two critical challenges remain. First, while masked autoregressive methods have recently outperformed diffusion-based approaches, existing masking models lack a mechanism to prioritize dynamic frames and body parts based on given conditions. Second, existing methods for different conditioning modalities often fail to integrate multiple modalities effectively, limiting control and coherence in generated motion. To address these challenges, we propose Motion Anything, a multimodal motion generation framework that introduces an Attention-based Mask Modeling approach, enabling fine-grained spatial and temporal control over key frames and actions. Our model adaptively encodes multimodal conditions, including text and music, improving controllability. Additionally, we introduce Text-Motion-Dance (TMD), a new motion dataset consisting of 2,153 pairs of text, music, and dance, making it twice the size of AIST++, thereby filling a critical gap in the community. Extensive experiments demonstrate that Motion Anything surpasses state-of-the-art methods across multiple benchmarks, achieving a 15% improvement in FID on HumanML3D and showing consistent performance gains on AIST++ and TMD. See our project website https://steve-zeyu-zhang.github.io/MotionAnything","url_abs":"https://arxiv.org/abs/2503.06955v1","url_pdf":"https://arxiv.org/pdf/2503.06955v1.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":"motion-anything-any-to-motion-generation","repo_url":"https://github.com/steve-zeyu-zhang/MotionAnything","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"motion-generation","task_name":"Motion Generation"},{"task_slug":"motion-synthesis","task_name":"Motion Synthesis"}],"methods":[],"datasets_introduced":[{"slug":"tmd","name":"TMD","full_name":"Text-Music-Dance"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/motion-synthesis-on-aist","task":"Motion Synthesis","dataset":"AIST++","model":"Motion Anything","rank_in_archive_order":1,"of":12,"metrics":{"Beat alignment score":"0.2757","FID":"17.22"},"uses_additional_data":false},{"leaderboard":"/sota/motion-synthesis-on-humanml3d","task":"Motion Synthesis","dataset":"HumanML3D","model":"Motion Anything","rank_in_archive_order":1,"of":37,"metrics":{"Diversity":"9.521","FID":"0.028","Multimodality":"2.705","R Precision Top3":"0.829"},"uses_additional_data":false},{"leaderboard":"/sota/motion-synthesis-on-kit-motion-language","task":"Motion Synthesis","dataset":"KIT Motion-Language","model":"Motion Anything","rank_in_archive_order":1,"of":31,"metrics":{"Diversity":"10.94","FID":"0.131","Multimodality":"1.374","R Precision Top3":"0.802"},"uses_additional_data":false},{"leaderboard":"/sota/motion-synthesis-on-tmd","task":"Motion Synthesis","dataset":"TMD","model":"Motion Anything","rank_in_archive_order":1,"of":1,"metrics":{"BAS":"0.2094","FID":"21.46","MMDist":"5.34","MModality":"2.424"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2503.06955","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}