Surgical Video Generation on Cholec80 (test)
276.2FVDM2V VAE
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| M2V VAEFPS Rate=8, Conditioning=GT Seg.2025.06 | 276.2 | 22.4 | 12.9 | 0.358 | 0.447 | 0.806 | 0.53 | |
| S2M+M2V VAEFPS Rate=8, Conditioning=Pred Seg.2025.06 | 278 | 24.1 | 15.1 | 0.218 | 0.311 | 0.867 | 0.53 | |
| S2M+M2V VAEFPS Rate=1, Conditioning=Pred Seg.2025.06 | 312.4 | 47.1 | 17.2 | 0.137 | 0.27 | 0.697 | 0.44 | |
| M2V VAEFPS Rate=1, Conditioning=GT Seg.2025.06 | 351.4 | 48.9 | 22.1 | 0.321 | 0.476 | 0.745 | 0.49 | |
| CogVideoXFPS Rate=1, Conditioning=None2025.06 | 443.1 | 79.6 | 35.5 | 0.007 | 0.016 | 0.596 | 0.28 | |
| M2V RADIOFPS Rate=1, Conditioning=GT Seg.2025.06 | 640.8 | 72.7 | 36.3 | 0.207 | 0.406 | 0.682 | 0.4 | |
| CogVideoX ControlNetFPS Rate=1, Conditioning=GT Seg. Edges2025.06 | 640.9 | 82.6 | 28.7 | 0.028 | 0.061 | 0.616 | 0.38 | |
| EndoraFPS Rate=1, Conditioning=None2025.06 | 815.8 | 105.2 | 60.3 | — | — | — | 0.16 | |
| M2V RADIOFPS Rate=8, Conditioning=GT Seg.2025.06 | 1,202.4 | 71.7 | 33.5 | 0.076 | 0.157 | 0.635 | 0.35 | |
| VISAGEFPS Rate=1, Conditioning=Triplet2025.06 | 1,780 | — | — | — | — | — | 0.56 |