A new representation, AV-MSF, predicts an object's impact sound at arbitrary contact points from multi-view images and only a few recordings, using visual features to guide a physics-based modal sound model.
In: CVPR (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Objects as Audio-Visual Modal Sound Fields
A new representation, AV-MSF, predicts an object's impact sound at arbitrary contact points from multi-view images and only a few recordings, using visual features to guide a physics-based modal sound model.