Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Free-T2M (StableMoFusion)

Free-T2M (StableMoFusion)

Reported on 24 benchmarks across 4 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio12 results

10-shot image generationonHumanML3D
Diversity· 2025-01-30
9.48
best: 23.692 (Diffuion Motion)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
10-shot image generationonHumanML3D
FID· 2025-01-30
0.051
best: 0.028 (Motion Anything)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
10-shot image generationonHumanML3D
R Precision Top3· 2025-01-30
0.803
best: 0.842 (MotionPCM)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
10-shot image generationonKIT Motion-Language
Diversity· 2025-01-30
10.902
best: 11.198 (T2M-GPT (τ = 0))
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
10-shot image generationonKIT Motion-Language
FID· 2025-01-30
0.155
best: 0.131 (Motion Anything)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
10-shot image generationonKIT Motion-Language
R Precision Top3· 2025-01-30
0.789
best: 0.803 (BiPO)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
3D Human Pose TrackingonHumanML3D
Diversity· 2025-01-30
9.48
best: 23.692 (Diffuion Motion)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
3D Human Pose TrackingonHumanML3D
FID· 2025-01-30
0.051
best: 0.028 (Motion Anything)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
3D Human Pose TrackingonHumanML3D
R Precision Top3· 2025-01-30
0.803
best: 0.842 (MotionPCM)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
3D Human Pose TrackingonKIT Motion-Language
Diversity· 2025-01-30
10.902
best: 11.198 (T2M-GPT (τ = 0))
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
3D Human Pose TrackingonKIT Motion-Language
FID· 2025-01-30
0.155
best: 0.131 (Motion Anything)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
3D Human Pose TrackingonKIT Motion-Language
R Precision Top3· 2025-01-30
0.789
best: 0.803 (BiPO)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232

Computer Vision6 results

Pose TrackingonHumanML3D
Diversity· 2025-01-30
9.48
best: 23.692 (Diffuion Motion)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
Pose TrackingonHumanML3D
FID· 2025-01-30
0.051
best: 0.028 (Motion Anything)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
Pose TrackingonHumanML3D
R Precision Top3· 2025-01-30
0.803
best: 0.842 (MotionPCM)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
Pose TrackingonKIT Motion-Language
Diversity· 2025-01-30
10.902
best: 11.198 (T2M-GPT (τ = 0))
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
Pose TrackingonKIT Motion-Language
FID· 2025-01-30
0.155
best: 0.131 (Motion Anything)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
Pose TrackingonKIT Motion-Language
R Precision Top3· 2025-01-30
0.789
best: 0.803 (BiPO)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232

Computer Code6 results

Motion SynthesisonHumanML3D
Diversity· 2025-01-30
9.48
best: 23.692 (Diffuion Motion)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
Motion SynthesisonHumanML3D
FID· 2025-01-30
0.051
best: 0.028 (Motion Anything)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
Motion SynthesisonHumanML3D
R Precision Top3· 2025-01-30
0.803
best: 0.842 (MotionPCM)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
Motion SynthesisonKIT Motion-Language
Diversity· 2025-01-30
10.902
best: 11.198 (T2M-GPT (τ = 0))
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
Motion SynthesisonKIT Motion-Language
FID· 2025-01-30
0.155
best: 0.131 (Motion Anything)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232
Motion SynthesisonKIT Motion-Language
R Precision Top3· 2025-01-30
0.789
best: 0.803 (BiPO)
Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss arXiv:2501.18232