Learn to Modify: Self-evolving Multi-agent Refinement Framework for Conversational Text-to-Motion Generation
Open paper
Benchmark
Model
Rank
Results
motion-synthesis-on-humanml3d
SMART
–
FID: 0.075
R Precision Top3: 0.827
Diversity: 9.277
motion-synthesis-on-kit-motion-language
SMART
–
FID: 0.255
R Precision Top3: 0.784
Diversity: 10.898
Rank counts only results with a code link.