Video Generation On Kinetics 600 12 Frames
評価指標
FVD
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | FVD | Paper Title | Repository |
---|---|---|---|
MAGVIT | 9.9 | MAGVIT: Masked Generative Video Transformer | |
MAGVIT-v2 | 4.3±0.1 | Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation | |
W.A.L.T-L | 3.3±0.0 | Photorealistic Video Generation with Diffusion Models | - |
DVD-GAN | 31.1 | Adversarial Video Generation on Complex Datasets |
0 of 4 row(s) selected.