FoleySpace generates binaural audio from silent video by estimating a 3D sound-source trajectory from object detection and depth and conditioning a diffusion model on that trajectory plus monaural audio.
Generating visually aligned sound from videos,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FoleySpace: Vision-Aligned Binaural Spatial Audio Generation
FoleySpace generates binaural audio from silent video by estimating a 3D sound-source trajectory from object detection and depth and conditioning a diffusion model on that trajectory plus monaural audio.