Video Generation on FaceForensics
9.02FVDGT
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| GT2021.04 | 9.02 | 0.2935 | — | — | — | |
| FrameDiT-HNumber of frames=16, Resolution=256 × 2562026.03 | 16.6 | — | — | — | — | |
| FrameDiT-GNumber of frames=16, Resolution=256 × 2562026.03 | 21.5 | — | — | — | — | |
| LatteNumber of frames=16, Resolution=256 × 2562026.03 | 27.1 | — | — | — | — | |
| StyleGAN-VNumber of frames=16, Resolution=256 × 2562026.03 | 47.4 | — | — | — | — | |
| MoCoGAN-HD2021.04 | 53.26 | 0.33 | 73.6 | — | — | |
| FVDMNumber of frames=16, Resolution=256 × 2562026.03 | 55 | — | — | — | — | |
| TGANv22021.04 | 58.03 | 0.4914 | 26.4 | — | — | |
| DIGANNumber of frames=16, Resolution=256 × 2562026.03 | 62.5 | — | — | — | — | |
| AR-DiffusionNumber of frames=16, Resolution=256 × 2562026.03 | 71.9 | — | — | — | — | |
| AR-DiffusionNumber of frames=16, Resolution=256 × 256, Checkpoint=Official2026.03 | 84 | — | — | — | — | |
| Diffusion ForcingNumber of frames=16, Resolution=256 × 2562026.03 | 99.5 | — | — | — | — | |
| MoCoGANNumber of frames=16, Resolution=256 × 2562026.03 | 124.7 | — | — | — | — | |
| VideoGPTNumber of frames=16, Resolution=256 × 2562026.03 | 185.9 | — | — | — | — | |
| PVDMNumber of frames=16, Resolution=256 × 2562026.03 | 355.9 | — | — | — | — | |
| DIGANTraining cost (GPU-days)=162021.12 | — | — | — | 62.5 | 1,824.7 | |
| MoCOGANTraining cost (GPU-days)=52021.12 | — | — | — | 124.7 | 257.3 | |
| MoCOGAN + StyleGAN2 backboneTraining cost (GPU-days)=82021.12 | — | — | — | 55.62 | 309.3 | |
| MoCOGAN-HDTraining cost (GPU-days)=7.5 + 92021.12 | — | — | — | 111.8 | 653 | |
| StyleGAN-VTraining cost (GPU-days)=82021.12 | — | — | — | 47.41 | 89.34 | |
| VideoGPTTraining cost (GPU-days)=16 + 162021.12 | — | — | — | 185.9 | — |