Sound-conditional video synthesis on AudioSet Drums 64x64
0.987SSIM (t=16)CCVS
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| CCVSConditioning frames=15, Audio conditioning=True2021.07 | 0.987 | 0.956 | 0.945 | 33.7 | 28.4 | 27.3 | |
| Sound2SightConditioning frames=15, Audio conditioning=True2021.07 | 0.984 | 0.954 | 0.947 | 33.2 | 27.9 | 27 | |
| SVG-LPConditioning frames=15, Audio conditioning=True2021.07 | 0.971 | 0.661 | 0.51 | 30 | 16.6 | 13.5 | |
| Vougioukas et al.Conditioning frames=15, Audio conditioning=True2021.07 | 0.94 | 0.904 | 0.896 | 26.2 | 23.8 | 23.3 |