{"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/free-t2m-frequency-enhanced-text-to-motion","title":"Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss","arxiv_id":"2501.18232","date":"2025-01-30","proceeding":null,"authors":["Wenshuo Chen","Haozhe Jia","Songning Lai","Keming Wu","Hongru Xiao","Lijie Hu","Yutao Yue"],"abstract":"Rapid progress in text-to-motion generation has been largely driven by diffusion models. However, existing methods focus solely on temporal modeling, thereby overlooking frequency-domain analysis. We identify two key phases in motion denoising: the **semantic planning stage** and the **fine-grained improving stage**. To address these phases effectively, we propose **Fre**quency **e**nhanced **t**ext-**to**-**m**otion diffusion model (**Free-T2M**), incorporating stage-specific consistency losses that enhance the robustness of static features and improve fine-grained accuracy. Extensive experiments demonstrate the effectiveness of our method. Specifically, on StableMoFusion, our method reduces the FID from **0.189** to **0.051**, establishing a new SOTA performance within the diffusion architecture. These findings highlight the importance of incorporating frequency-domain insights into text-to-motion generation for more precise and robust results.","url_abs":"https://arxiv.org/abs/2501.18232v1","url_pdf":"https://arxiv.org/pdf/2501.18232v1.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":"free-t2m-frequency-enhanced-text-to-motion","repo_url":"https://github.com/Hxxxz0/Free-T2m","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"motion-generation","task_name":"Motion Generation"},{"task_slug":"motion-synthesis","task_name":"Motion Synthesis"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/motion-synthesis-on-humanml3d","task":"Motion Synthesis","dataset":"HumanML3D","model":"Free-T2M (StableMoFusion)","rank_in_archive_order":7,"of":37,"metrics":{"Diversity":"9.480","FID":"0.051","R Precision Top3":"0.803"},"uses_additional_data":false},{"leaderboard":"/sota/motion-synthesis-on-kit-motion-language","task":"Motion Synthesis","dataset":"KIT Motion-Language","model":"Free-T2M (StableMoFusion)","rank_in_archive_order":2,"of":31,"metrics":{"Diversity":"10.902","FID":"0.155","R Precision Top3":"0.789"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}