Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Audio-driven Facial Animation on (test)
Loading...
1.33
MSE (mm)
DiffPoseTalk
1.2832
1.5991
1.915
2.2309
May 29, 2026
MSE (mm)
LVE (mm)
FDD ($10^{-5}$m)
MOD (mm)
Updated 2d ago
Evaluation Results
Method
Method
Links
MSE (mm)
LVE (mm)
FDD ($10^{-5}$m)
MOD (mm)
DiffPoseTalk
2026.05
1.33
13.64
4.33
2.68
GLM-4-Voice
category=Adaptation Layer
2026.05
1.35
14.02
4.44
2.96
CosyVoice2
category=Adaptation Layer
2026.05
1.37
14.26
4.34
2.94
TokTalk w/ style
style=with
2026.05
1.39
14.53
4.29
2.82
MSMD
2026.05
1.54
16.07
11.19
2.65
TokTalk w/o style
style=without
2026.05
2.11
20.73
4.45
3.15
FaceFormer
2026.05
2.5
24.02
5.19
3.77
Feedback
Search any
task
Search any
task