Logo image
Physics-Aware Novel-View Acoustic Synthesis with Vision-Language Priors and 3D Acoustic Environment Modeling
Conference paper

Physics-Aware Novel-View Acoustic Synthesis with Vision-Language Priors and 3D Acoustic Environment Modeling

Wenwu Wang, Congyi Fan, Jian Guan, Youtian Lin, Dongli Xu, Tong Ye, Qiaoxi Zhu and Pengming Feng
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2026)
Institute of Electrical and Electronics Engineers (IEEE)
The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2026 (Barcelona, Spain, 04/05/2026–08/05/2026)
17/01/2026

Abstract

physics- aware feature representation vision-language priors Novel-view acoustic synthesis
Spatial audio is essential for immersive experiences, yet novel-view acoustic synthesis (NVAS) remains challenging due to complex physical phenomena such as reflection , diffraction, and material absorption. Existing methods based on single-view or panoramic inputs improve spatial fidelity but fail to capture global geometry and semantic cues such as object layout and material properties. To address this, we propose Phys-NVAS, the first physics-aware NVAS framework that integrates spatial geometry modeling with vision–language semantic priors. A global 3D acoustic environment is reconstructed from multi-view images and depth maps to estimate room size and shape, enhancing spatial awareness of sound propagation. Meanwhile, a vision–language model extracts physics-aware priors of objects, layouts, and materials, capturing absorption and reflection beyond geometry. An acoustic feature fusion adapter unifies these cues into a physics-aware representation for bin-aural generation. Experiments on RWAVS demonstrate that Phys-NVAS yields binaural audio with improved realism and physical consistency.
pdf
AV_3D_audio_CR2.26 MB
Author's Accepted Manuscript CC BY V4.0 Restricted. Access maybe granted on request., This file will be open access upon publication.
url
https://2026.ieeeicassp.org/View
Event WebsiteConference website

Metrics

1 Record Views

Details

Logo image

Usage Policy