Papers › Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss
Wenshuo Chen, Haozhe Jia, Songning Lai, Keming Wu, Hongru Xiao, Lijie Hu, Yutao Yue
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.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Motion Synthesis | HumanML3D | Free-T2M (StableMoFusion) | Diversity | 9.480 | #7 of 37 | Archive leaderboard | report |
| Motion Synthesis | HumanML3D | Free-T2M (StableMoFusion) | FID | 0.051 | #7 of 37 | Archive leaderboard | report |
| Motion Synthesis | HumanML3D | Free-T2M (StableMoFusion) | R Precision Top3 | 0.803 | #7 of 37 | Archive leaderboard | report |
| Motion Synthesis | KIT Motion-Language | Free-T2M (StableMoFusion) | Diversity | 10.902 | #2 of 31 | Archive leaderboard | report |
| Motion Synthesis | KIT Motion-Language | Free-T2M (StableMoFusion) | FID | 0.155 | #2 of 31 | Archive leaderboard | report |
| Motion Synthesis | KIT Motion-Language | Free-T2M (StableMoFusion) | R Precision Top3 | 0.789 | #2 of 31 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections