360° Video Generation on 150-clip suite PanoGeo Argus Habitat-Sim 1.0 (test)
28.5FVDPanoWorld
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| PanoWorldInput Protocol=Stage 2, Input=single ERP first frame + caption (frame-0 anchored), Base Model=Cosmos 2.52026.05 | 28.5 | 41.5 | 55.4 | 0.253 | 0.981 | 0.032 | 0.896 | |
| OmniRoamInput Protocol=Stage 2, Input=single ERP first frame + caption (frame-0 anchored), Base Model=WAN 2.12026.05 | 39.7 | 53.6 | 69.7 | 0.233 | 0.774 | 0.147 | 0.628 | |
| PanoWorldInput Protocol=Stage 1, Input=single perspective image + caption, Base Model=Cosmos 2.52026.05 | 56.1 | 83.4 | 136.4 | 0.264 | 0.025 | 0.013 | 0.994 | |
| ARGUSInput Protocol=Stage 1, Input=single perspective image + caption, Base Model=SVD2026.05 | 65 | 82.7 | 152.5 | 0.212 | 0.032 | 0.021 | 0.993 | |
| Imagine360Input Protocol=Stage 1, Input=single perspective image + caption, Base Model=AnimateDiff2026.05 | 67.7 | 96.6 | 142.9 | 0.253 | 0.115 | 0.045 | 0.915 | |
| Follow-Your-CanvasInput Protocol=Stage 1, Input=single perspective image + caption, Base Model=AnimateDiff2026.05 | 82.2 | 108.8 | 182.3 | 0.279 | 0.113 | 0.048 | 0.935 | |
| OmniRoamInput Protocol=Stage 1, Input=single perspective image + caption, Base Model=WAN 2.12026.05 | 98.8 | 131.2 | 178.4 | 0.132 | 4.079 | 0.299 | 0.231 | |
| 360DVDInput Protocol=Stage 1, Input=single perspective image + caption, Base Model=AnimateDiff2026.05 | 100.7 | 94.6 | 191.8 | 0.262 | 0.204 | 0.038 | 0.922 |