Video on Cityscapes 128x128
Metric: Train (higher is better)
Metric: Train (higher is better)
| # | Model↕ | Train▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GHVAEs | 10 | No | Greedy Hierarchical Variational Autoencoders for... | 2021-03-06 | - |
| 2 | Hier-VRNN | 10 | No | Improved Conditional VRNNs for Video Prediction | 2019-04-27 | Code |
| 3 | SVG (from Hier-VRNN) | 10 | No | Stochastic Video Generation with a Learned Prior | 2018-02-21 | Code |