Learning Acoustic Scattering Fields for Dynamic Interactive Sound Propagation

TL;DR

This paper introduces a hybrid neural network and ray tracing method for real-time, dynamic sound propagation that captures complex acoustic effects with high efficiency and perceptual realism.

Contribution

It proposes a novel neural network-based scattered field representation combined with geometric deep learning for interactive sound simulation in dynamic scenes.

Findings

Achieves real-time performance with minimal overhead.

Accurately models diffraction and occlusion effects.

User study confirms perceptual improvements.

Abstract

We present a novel hybrid sound propagation algorithm for interactive applications. Our approach is designed for dynamic scenes and uses a neural network-based learned scattered field representation along with ray tracing to generate specular, diffuse, diffraction, and occlusion effects efficiently. We use geometric deep learning to approximate the acoustic scattering field using spherical harmonics. We use a large 3D dataset for training, and compare its accuracy with the ground truth generated using an accurate wave-based solver. The additional overhead of computing the learned scattered field at runtime is small and we demonstrate its interactive performance by generating plausible sound effects in dynamic scenes with diffraction and occlusion effects. We demonstrate the perceptual benefits of our approach based on an audio-visual user study.