| Paper | Code | FVD | SSIM | PSNR | LPIPS | Cond. | Train | Pred | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|---|---|
| Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction | 418.00 ± 5.0 | 0.740±0.4 | 0.193 ± 0.014 | 2 | 10 | 28 | GHVAEs | 2021-03-06 | ||
| Improved Conditional VRNNs for Video Prediction | ✓ Link | 567.51 | 0.628±0.1 | 0.264 ± .07 | 2 | 10 | 28 | Hier-VRNN | 2019-04-27 | |
| Stochastic Video Generation with a Learned Prior | ✓ Link | 1300.26 | 0.574±0.08 | 0.549 ± 0.06 | 2 | 10 | 28 | SVG (from Hier-VRNN) | 2018-02-21 | |
| SLAMP: Stochastic Latent Appearance and Motion Prediction | ✓ Link | 0.649±0.025 | 21.73±0.76 | 0.2941±0.022 | 10 | 20 | SLAMP | 2021-08-05 | ||
| Stochastic Latent Residual Video Prediction | ✓ Link | 0.603±0.016 | 20.97±0.43 | 0.447±0.014 | 10 | 20 | SRVP | 2020-02-21 |