Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model
Open paper
Benchmark
Model
Rank
Results
motion-synthesis-on-humanml3d
Fg-T2M
–
FID: 0.243
R Precision Top3: 0.783
Diversity: 9.278
…
motion-synthesis-on-kit-motion-language
Fg-T2M
–
FID: 0.571
R Precision Top3: 0.745
Diversity: 10.93
…
Rank counts only results with a code link.