Passive scene audio, especially direction-of-arrival cues, improves relative camera pose estimation when combined with vision in real-world videos.
Mavil: Masked audio-video learners
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
-
Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video
Passive scene audio, especially direction-of-arrival cues, improves relative camera pose estimation when combined with vision in real-world videos.