Video Prediction on RoboNet (test)
53.3FVDMOSO
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| MOSOParams=265M, H x W=64x642023.03 | 53.3 | 31.2 | 0.921 | 0.017 | |
| FitVidParams=302M, H x W=64x642023.03 | 62.5 | 28.2 | 0.893 | 0.024 | |
| MOSOParams=265M, H x W=256x2562023.03 | 91.5 | 26.3 | 0.799 | 0.096 | |
| GHVAEParams=599M, H x W=64x642023.03 | 95.2 | 24.7 | 0.891 | 0.036 | |
| SVGParams=298M, H x W=64x642023.03 | 123.2 | 23.9 | 0.878 | 0.06 | |
| MaskViTParams=257M, H x W=64x642023.03 | 133.5 | 23.2 | 0.805 | 0.042 | |
| MaskViTParams=228M, H x W=256x2562023.03 | 211.7 | 20.4 | 0.671 | 0.17 |