| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Prediction | BAIR (test) | FVD82.64 | 59 | |
| Video Prediction | BAIR | FVD83.6 | 34 | |
| Future Video Prediction | BAIR 64x64 and 256x256 (test) | FVD50 | 16 | |
| Frame Prediction | BAIR | FVD62 | 15 | |
| Video Prediction | BAIR 64x64 | FVD86.9 | 14 | |
| Video Prediction | BAIR 64x64 (test) | SSIM0.849 | 12 | |
| Video Prediction | BAIR 64 x 64 1 -> 15 | FVD89.5 | 11 | |
| Trajectory Prediction and Robot Action Planning | BAIR | PSNR20.3 | 7 | |
| Video Interpolation | BAIR 64 x 64 (test) | PSNR25.162 | 7 | |
| Video Prediction | BAIR 64 x 64 2 -> 28 | FVD118.4 | 7 | |
| Video Generation | BAIR | FVD Score120.03 | 7 | |
| Video Motion Transfer | BAIR (test) | APD-to-MAE Ratio1.3337 | 6 | |
| Keypoint Prediction | BAIR (test) | Energy Distance7.3468 | 6 | |
| Video Prediction | BAIR 64 x 64 2 -> 14 | FVD87.9 | 6 | |
| Proxy-supervised Video Generation | BAIR 64x64 Full (test) | LPIPS0.154 | 6 | |
| Point-to-point video synthesis | BAIR 64x64 (test) | SSIM (Best)0.857 | 4 | |
| Spatiotemporal Prediction | BAIR | RMSE11.54 | 3 | |
| Video reconstruction | Bair | L1 Loss0.027 | 3 | |
| Image Animation | Bair | User Preference Rate95 | 2 | |
| Video Generation | BAIR action-free (test) | Bits-per-pixel1.87 | 1 | |
| Video Prediction | BAIR Balanced (B) | Metric- | 0 |