Video Prediction on BAIR 64x64 (test)
62FVDMAGVIT-L
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| MAGVIT-LResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 62 | — | — | — | |
| VDMResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 66.9 | — | — | — | |
| CVPResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 70.1 | — | — | — | |
| RIVERResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 73.5 | — | — | — | |
| MAGVIT-BResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 76 | — | — | — | |
| ExtDM-K4Params=121 M, context frames (c)=2, predicted frames (p)=142025.03 | 81.6 | 0.845 | 20.04 | 0.053 | |
| RaMViDResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 84.2 | — | — | — | |
| NUWAResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 86.9 | — | — | — | |
| MCVD-cpParams=565 M, context frames (c)=2, predicted frames (p)=142025.03 | 87.8 | 0.838 | 19.1 | 0.075 | |
| LPWMResolution=64 x 64, Conditioning frames=1, Predicted frames=15, Model Size=100M2026.03 | 89.4 | — | — | — | |
| MCVDResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 89.5 | — | — | — | |
| FitVidResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 93.6 | — | — | — | |
| CCVSResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 99 | — | — | — | |
| FAR-BParams=130 M, context frames (c)=2, predicted frames (p)=142025.03 | 99.3 | 0.849 | 20.87 | 0.038 | |
| ExtDM-K4Params=121 M, context frames (c)=2, predicted frames (p)=282025.03 | 102.8 | 0.814 | 18.74 | 0.069 | |
| TrIVD-GAN-FPResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 103.3 | — | — | — | |
| VideoGPTResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 103.3 | — | — | — | |
| DVD-GAN-FPResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 109.8 | — | — | — | |
| MCVD-cpParams=565 M, context frames (c)=2, predicted frames (p)=282025.03 | 119 | 0.797 | 17.7 | 0.078 | |
| LVTResolution=64 x 64, Conditioning frames=1, Predicted frames=152026.03 | 125.8 | — | — | — | |
| VIDMParams=194 M, context frames (c)=2, predicted frames (p)=142025.03 | 131.7 | 0.763 | 16.97 | 0.08 | |
| FAR-BParams=130 M, context frames (c)=2, predicted frames (p)=282025.03 | 144.3 | 0.819 | 19.4 | 0.049 | |
| RaMViDParams=235 M, context frames (c)=2, predicted frames (p)=142025.03 | 166.5 | 0.758 | 17.55 | 0.085 | |
| LFDMParams=108 M, context frames (c)=2, predicted frames (p)=142025.03 | 167.6 | 0.77 | 17.45 | 0.084 | |
| VIDMParams=194 M, context frames (c)=2, predicted frames (p)=282025.03 | 194.6 | 0.728 | 16.16 | 0.096 | |
| RaMViDParams=235 M, context frames (c)=2, predicted frames (p)=282025.03 | 238.7 | 0.691 | 16.51 | 0.109 | |
| LFDMParams=108 M, context frames (c)=2, predicted frames (p)=282025.03 | 276.8 | 0.728 | 16.2 | 0.106 |