Point-based Acoustic Scattering for Interactive Sound Propagation via Surface Encoding

TL;DR

This paper introduces a real-time neural network method that uses point cloud surface encoding to accurately compute acoustic scattering for interactive sound propagation in dynamic scenes.

Contribution

It presents the first real-time learning algorithm for high-accuracy acoustic scattering approximation of arbitrary objects using surface encoding and neural networks.

Findings

Handles objects with arbitrary topology and deformation.

Achieves less than 1ms computation per object on standard GPU.

Outperforms existing point-based geometric deep learning methods.

Abstract

We present a novel geometric deep learning method to compute the acoustic scattering properties of geometric objects. Our learning algorithm uses a point cloud representation of objects to compute the scattering properties and integrates them with ray tracing for interactive sound propagation in dynamic scenes. We use discrete Laplacian-based surface encoders and approximate the neighborhood of each point using a shared multi-layer perceptron. We show that our formulation is permutation invariant and present a neural network that computes the scattering function using spherical harmonics. Our approach can handle objects with arbitrary topologies and deforming models, and takes less than 1ms per object on a commodity GPU. We have analyzed the accuracy and perform validation on thousands of unseen 3D objects and highlight the benefits over other point-based geometric deep learning methods. To the best of our knowledge, this is the first real-time learning algorithm that can approximate the acoustic scattering properties of arbitrary objects with high accuracy.