Video Generation On Taichi
평가 지표
FVD16
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | FVD16 | Paper Title | Repository |
|---|---|---|---|
| StyleSV (256x256) | 82.6 | Towards Smooth Video Composition | |
| DIGAN (256x256) | 156.7 | Latent Video Diffusion Models for High-Fidelity Long Video Generation | |
| LVDM (256x256) | 99 | Latent Video Diffusion Models for High-Fidelity Long Video Generation | |
| TATS (128x128) | 94.6 | Latent Video Diffusion Models for High-Fidelity Long Video Generation | |
| MoCoGAN-HD (128x128) | 144.7 | Latent Video Diffusion Models for High-Fidelity Long Video Generation | |
| DIGAN (128x128) | 128.1 | Latent Video Diffusion Models for High-Fidelity Long Video Generation |
0 of 6 row(s) selected.