A latent diffusion audio model is trained to ground sound in image patches, then uses SAM segmentation masks at test time so users can generate audio for selected objects in a scene.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sounding that Object: Interactive Object-Aware Image to Audio Generation
A latent diffusion audio model is trained to ground sound in image patches, then uses SAM segmentation masks at test time so users can generate audio for selected objects in a scene.