Joint Video-Audio Generation on Landscape (test)
86.79FVDAVDiT (MoNL)
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| AVDiT (MoNL)2024.05 | 86.79 | 4.3 | — | 0.57 | |
| JavisDiT2025.03 | 94.2 | 7.8 | 8.5 | — | |
| MM-LDM2025.03 | 105 | 8.3 | 9.1 | — | |
| AV-DiT2025.03 | 172.7 | 15.4 | 11.2 | — | |
| MM-Diffusion (MMD)2024.05 | 238.33 | 15.14 | — | 0.54 | |
| See&Hear2025.03 | 326.2 | 9.2 | 12.7 | — | |
| MM-Diff2025.03 | 332.1 | 26.6 | 9.9 | — | |
| MMdomain=Landscape2024.02 | 1,141.009 | 135.368 | 7.752 | — | |
| MM + Diffusion Latent Alignerdomain=Landscape, denoising_steps=252024.02 | 1,174.856 | 135.422 | 6.463 | — |