AV-GS: learning material and geometry aware priors for novel view acoustic synthesis
Author(s)
Bhosale, S
Yang, H
Kanojia, D
Deng, J
Zhu, X
Type
Conference Paper
Abstract
Novel view acoustic synthesis (NVAS) aims to render binaural audio at any target viewpoint, given a mono audio emitted by a sound source at a 3D scene. Existing methods have proposed NeRF-based implicit models to exploit visual cues as a condition for synthesizing binaural audio. However, in addition to low efficiency originating from heavy NeRF rendering, these methods all have a limited ability of characterizing the entire scene environment such as room geometry, material properties, and the spatial relation between the listener and sound source. To address these issues, we propose a novel Audio-Visual Gaussian Splatting (AV-GS) model. To obtain an implicit material-aware and geometry-aware condition for audio synthesis, we learn an explicit point-based scene representation with an audio-guidance parameter on locally initialized Gaussian points, taking into account the space relation from the listener and sound source. To make the visual scene model audio adaptive, we propose a point densification and pruning strategy to optimally distribute the Gaussian points, with the per-point contribution in sound propagation (e.g., more points needed for texture-less wall surfaces as they affect sound path diversion). Extensive experiments validate the superiority of our AV-GS over existing alternatives on the real-world RWAS and simulation-based SoundSpaces datasets. Project page: https://surrey-uplab.github.io/research/avgs/.
Date Issued
2025-02-01
Date Acceptance
2024-12-01
Citation
Advances in Neural Information Processing Systems, 2025, 37, pp.28920-28937
ISBN
9798331314385
ISSN
1049-5258
Publisher
Neural Information Processing Systems Foundation, Inc. (NeurIPS)
Start Page
28920
End Page
28937
Journal / Book Title
Advances in Neural Information Processing Systems
Volume
37
Copyright Statement
© 2025 Neural Information Processing Systems Foundation, Inc. (NeurIPS).
Source
NeurIPS 2024
Publication Status
Published
Start Date
2024-12-10
Finish Date
2024-12-15
Coverage Spatial
Vancouver, Canada