Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space
Open paper
Benchmark
Model
Rank
Results
video-to-sound-generation-on-vggsound-v2a
Flowley + SoundCap
#6
KL (PaSST): 1.56
ImageBind Score: 30.07
IS (PANNs): 19.68
Rank counts only results with a code link.