List your company

Foley Generation on VGGSound (test)

11.73FIDMel-QCD
11.308814.151916.99519.8381Mar 10, 2025

Evaluation results

MethodLinks
Mel-QCD2025.0311.732.960.45910.330.110.25420.520.31———————
VTA-LDM2025.0311.774.720.27720.370.110.26830.440.28———————
FoleyCrafter2025.0313.114.140.31540.430.130.24330.480.29———————
DiffFoley2025.0315.156.470.23270.490.140.16020.320.23———————
Im2Wav2025.0316.165.660.1670.450.130.2210.310.2———————
SpecVQGAN2025.0319.316.470.05640.450.10.24340.180.13———————
Seeing-and-Hearing2025.0320.326.080.10560.680.170.20490.430.38———————
Auffusion2025.0322.265.540.18360.440.120.2230.350.22———————
AC-FoleyComparison Baseline=MMAudio-L-V22026.03————————————61.121.883.5
MultiFoleyConditioning=text control, Evaluation protocol=Human evaluation (2AFC) win rate against FoleyCrafter2024.11————————85.894.586.590.2———