Video Generation on Robotic Manipulation Tasks (test)
19.577PSNROurs-Full
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Ours-FullGuidance=Joint Control and Visual Dynamics2026.04 | 19.577 | 0.6484 | 0.8102 | 0.2647 | 147.9 | 15.765 | |
| Ours-VDGuidance=Visual Dynamics only2026.04 | 18.153 | 0.5916 | 0.7884 | 0.2813 | 153.12 | 22.311 | |
| BaselineArchitecture=UNet-based diffusion2026.04 | 16.849 | 0.5129 | 0.7526 | 0.3494 | 254.59 | 50.369 | |
| Sim2026.04 | 16.443 | 0.4342 | 0.7564 | 0.3629 | 187.4 | 61.048 | |
| Zero-Shotsim-to-real domain adaptation=false2026.04 | 13.093 | 0.5487 | 0.7308 | 0.4756 | 219.74 | 163.83 | |
| Ours-CDGuidance=Control Dynamics only2026.04 | 8.464 | 0.1486 | 0.7216 | 0.813 | 434.44 | 239.13 |