Scene-aware text-driven motion generation on Scene-aware motion generation (test)
0.803RP@3SceneAdapt
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| SceneAdaptGroup=Ours, T-M=true, T-S-M=false, S-M=true, ws=0.02025.10 | 0.803 | 0.312 | 0.298 | 0.273 | 0.299 | |
| MDMGroup=Baseline, T-M=true, T-S-M=false, S-M=false, Inf. Time (s)=0.522025.10 | 0.798 | 0.479 | 0.316 | 0.319 | 0.344 | |
| SceneAdaptGroup=Ours, T-M=true, T-S-M=false, S-M=true, ws=0.32025.10 | 0.792 | 0.497 | 0.256 | 0.208 | 0.246 | |
| SceneAdaptGroup=Ours, T-M=true, T-S-M=false, S-M=true, ws=0.5, Inf. Time (s)=1.692025.10 | 0.75 | 1.42 | 0.22 | 0.16 | 0.199 | |
| SceneAdaptGroup=Ours, T-M=true, T-S-M=false, S-M=true, ws=1.02025.10 | 0.588 | 7.389 | 0.136 | 0.076 | 0.101 | |
| MDM + ControlNetGroup=Feed forward, T-M=true, T-S-M=true, S-M=false, Inf. Time (s)=1.792025.10 | 0.365 | 36.19 | 0.142 | 0.041 | 0.064 | |
| SceneAdaptGroup=Ours, T-M=true, T-S-M=false, S-M=true, ws=2.02025.10 | 0.365 | 18.88 | 0.072 | 0.035 | 0.045 | |
| AffordMotionGroup=Feed forward, T-M=true, T-S-M=true, S-M=false, Inf. Time (s)=51.282025.10 | 0.305 | 6.32 | 0.429 | 0.254 | 0.321 | |
| AffordMotionGroup=Feed forward, T-M=false, T-S-M=true, S-M=false, Inf. Time (s)=50.722025.10 | 0.14 | 21.59 | 0.257 | 0.059 | 0.097 | |
| DNOGroup=Optimization, T-M=true, T-S-M=false, S-M=false, Inf. Time (s)=332.962025.10 | 0.128 | 32.22 | 0.001 | 0.002 | 0.002 | |
| MDM + SceneCo LayerGroup=Feed forward, T-M=true, T-S-M=true, S-M=false, Inf. Time (s)=1.692025.10 | 0.094 | 80.89 | 0.05 | 0.004 | 0.005 | |
| HUMANISE cVAEGroup=Feed forward, T-M=false, T-S-M=true, S-M=false, Inf. Time (s)=0.172025.10 | 0.092 | 34.58 | 0.002 | 0.001 | 0.001 | |
| DARTControlGroup=Optimization, T-M=true, T-S-M=false, S-M=false, Inf. Time (s)=362.902025.10 | 0.056 | 53.29 | 0.01 | 0.007 | 0.01 |