Self-Supervised Generation of Spatial Audio for 360 Video
arXiv:1809.02587
Abstract
We introduce an approach to convert mono audio recorded by a 360 video camera into spatial audio, a representation of the distribution of sound over the full viewing sphere. Spatial audio is an important component of immersive 360 video viewing, but spatial audio microphones are still rare in current 360 video production. Our system consists of end-to-end trainable neural networks that separate individual sound sources and localize them on the viewing sphere, conditioned on multi-modal analysis of audio and 360 video frames. We introduce several datasets, including one filmed ourselves, and one collected in-the-wild from YouTube, consisting of 360 videos uploaded with spatial audio. During training, ground-truth spatial audio serves as self-supervision and a mixed down mono track forms the input to our network. Using our approach, we show that it is possible to infer the spatial location of sound sources based only on 360 video and a mono audio track.
arXiv commentTo appear in NIPS 2018
Cited by in corpus (21)
- Multimodality in VR: A survey
- Learning Representations from Audio-Visual Spatial Alignment
- Self-supervised Moving Vehicle Tracking with Stereo Sound
- Sound Synthesis, Propagation, and Rendering: A Survey
- Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation
- VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency
- Co-Separating Sounds of Visual Objects
- Foley Music: Learning to Generate Music from Videos
- VisualEchoes: Spatial Image Representation Learning through Echolocation
- Listen to Look: Action Recognition by Previewing Audio
- Points2Sound: From mono to binaural audio using 3D point cloud scenes
- SoundSpaces: Audio-Visual Navigation in 3D Environments
- Music Gesture for Visual Sound Separation
- Learning Audio-Visual Dereverberation
- Unsupervised Sound Localization via Iterative Contrastive Learning
- Visually Informed Binaural Audio Generation without Binaural Audios
- Vision-Infused Deep Audio Inpainting
- Self-supervised Audio Spatialization with Correspondence Classifier
- Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications
- V-SlowFast Network for Efficient Visual Sound Separation
- Binaural Audio Generation via Multi-task Learning