Learning Acoustic Scattering Fields for Dynamic Interactive Sound Propagation
This work addresses the challenge of realistic sound simulation for interactive applications like games or VR, though it is incremental as it builds on existing ray tracing and neural methods.
The paper tackled the problem of efficient sound propagation in dynamic interactive scenes by developing a hybrid algorithm that combines neural network-based learned scattered fields with ray tracing, achieving interactive performance with plausible sound effects including diffraction and occlusion, as demonstrated in a user study.
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.