PAVAS: Physics-Aware Video-to-Audio Synthesis
Open paper
Benchmark
Model
Rank
Results
video-to-sound-generation-on-vggsound-v2a
PAVAS-L
#1
FD (PaSST): 47.38
KL (PaSST): 1.35
ImageBind Score: 35.41
…
Rank counts only results with a code link.