English

SoundSpaces: Audio-Visual Navigation in 3D Environments

Computer Vision and Pattern Recognition 2020-08-25 v3 Human-Computer Interaction Sound Audio and Speech Processing

Abstract

Moving around in the world is naturally a multisensory experience, but today's embodied agents are deaf---restricted to solely their visual perception of the environment. We introduce audio-visual navigation for complex, acoustically and visually realistic 3D environments. By both seeing and hearing, the agent must learn to navigate to a sounding object. We propose a multi-modal deep reinforcement learning approach to train navigation policies end-to-end from a stream of egocentric audio-visual observations, allowing the agent to (1) discover elements of the geometry of the physical space indicated by the reverberating audio and (2) detect and follow sound-emitting targets. We further introduce SoundSpaces: a first-of-its-kind dataset of audio renderings based on geometrical acoustic simulations for two sets of publicly available 3D environments (Matterport3D and Replica), and we instrument Habitat to support the new sensor, making it possible to insert arbitrary sound sources in an array of real-world scanned environments. Our results show that audio greatly benefits embodied visual navigation in 3D spaces, and our work lays groundwork for new research in embodied AI with audio-visual perception.

Keywords

Cite

@article{arxiv.1912.11474,
  title  = {SoundSpaces: Audio-Visual Navigation in 3D Environments},
  author = {Changan Chen and Unnat Jain and Carl Schissler and Sebastia Vicenc Amengual Gari and Ziad Al-Halah and Vamsi Krishna Ithapu and Philip Robinson and Kristen Grauman},
  journal= {arXiv preprint arXiv:1912.11474},
  year   = {2020}
}

Comments

Accepted to ECCV 2020 (Spotlight). Project page: http://vision.cs.utexas.edu/projects/audio_visual_navigation/

R2 v1 2026-06-23T12:55:57.919Z