Class-conditional video generation on UCF-101 v1.0 (train test)
66.32FVDHPDM-L
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| HPDM-LResolution=16 x 256 x 256, Pre-trained=false, #samples=10,0002024.06 | 66.32 | 87.68 | |
| Make-A-VideoResolution=16 x 256 x 256, Pre-trained=true, #samples=10,0002024.06 | 81.25 | 82.55 | |
| HPDM-LResolution=16 x 256 x 256, Pre-trained=false, #samples=2,0482024.06 | 92 | 71.16 | |
| HPDM-LResolution=64 x 256 x 256, Pre-trained=false, #samples=10,0002024.06 | 101.42 | — | |
| HPDM-LResolution=64 x 256 x 256, Pre-trained=false, #samples=2,0482024.06 | 137.52 | — | |
| HPDM-MResolution=16 x 256 x 256, Pre-trained=false, #samples=10,0002024.06 | 143.06 | 84.29 | |
| VideoFusionResolution=16 x 128 x 128, Pre-trained=false2024.06 | 173 | 80.03 | |
| HPDM-MResolution=16 x 256 x 256, Pre-trained=false, #samples=2,0482024.06 | 178.15 | 69.76 | |
| HPDM-MResolution=64 x 256 x 256, Pre-trained=false, #samples=10,0002024.06 | 257.65 | — | |
| VIDMResolution=16 x 256 x 256, Pre-trained=false, #samples=2,0482024.06 | 294.7 | — | |
| HPDM-MResolution=64 x 256 x 256, Pre-trained=false, #samples=2,0482024.06 | 324.72 | — | |
| TATSResolution=16 x 128 x 128, Pre-trained=false2024.06 | 332 | 79.28 | |
| PVDMResolution=16 x 256 x 256, Pre-trained=false, #samples=2,0482024.06 | 343.6 | — | |
| HPDM-SResolution=16 x 256 x 256, Pre-trained=false, #samples=10,0002024.06 | 344.54 | 73.73 | |
| HPDM-SResolution=16 x 256 x 256, Pre-trained=false, #samples=2,0482024.06 | 370.5 | 61.5 | |
| LVDMResolution=16 x 256 x 256, Pre-trained=false, #samples=2,0482024.06 | 372 | — | |
| HPDM-SResolution=64 x 256 x 256, Pre-trained=false, #samples=10,0002024.06 | 578.8 | — | |
| HPDM-SResolution=64 x 256 x 256, Pre-trained=false, #samples=2,0482024.06 | 647.48 | — | |
| PVDMResolution=128 x 256 x 256, Pre-trained=false, #samples=2,0482024.06 | 648.4 | — | |
| StyleGAN-VResolution=16 x 256 x 256, Pre-trained=false, #samples=2,0482024.06 | 1,431 | 23.94 | |
| DIGANResolution=16 x 128 x 128, Pre-trained=false, #samples=2,0482024.06 | 1,630.2 | 0 | |
| PVDMResolution=16 x 256 x 256, Pre-trained=false, #samples=10,0002024.06 | — | 74.4 |