Sound Localization from Motion:
Jointly Learning Sound Direction and Camera Rotation


Ziyang Chen
Shengyi Qian
Andrew Owens

University of Michigan

ArXiv 2023

[Paper]
[Github]




Abstract

The images and sounds that we perceive undergo subtle but geometrically consistent changes as we rotate our heads. In this paper, we use these cues to solve a problem we call Sound Localization from Motion (SLfM): jointly estimating camera rotation and localizing sound sources. We learn to solve these tasks solely through self-supervision. A visual model predicts camera rotation from a pair of images, while an audio model predicts the direction of sound sources from binaural sounds. We train these models to generate predictions that agree with one another. At test time, the models can be deployed independently. To obtain a feature representation that is well-suited to solving this challenging problem, we also propose a method for learning an audio-visual representation through cross-view binauralization: estimating binaural sound from one view, given images and sound from another. Our model can successfully estimate accurate rotations on both real and synthetic scenes, and localize sound sources with accuracy competitive with state-of-the-art self-supervised approaches.




Qualitative Results


Predictions on HM3D-SS



Real-world Demo




Paper and Supplementary Material

Ziyang Chen, Shengyi Qian, Andrew Owens.
Sound Localization from Motion:
Jointly Learning Sound Direction and Camera Rotation.

ArXiv 2023.

(ArXiv)

[Bibtex]


Acknowledgements

This work was funded in part by DARPA Semafor and Sony. The views, opinions and/or findings expressed are those of the authors and should not be interpreted as representing the official views or policies of the Department of Defense or the U.S. Government. The webpage template was originally made by Phillip Isola and Richard Zhang for a Colorization project.