Fast 3D Acoustic Scattering via Discrete Laplacian Based Implicit Function Encoders

Hsien-Yu Meng, Zhenyu Tang, Dinesh Manocha

Keywords: wave equation, wave acoustics, geometric deep learning, sound simulation, shape laplacian

Abstract: Acoustic properties of objects corresponding to scattering characteristics are frequently used for 3D audio content creation, environmental acoustic effects, localization and acoustic scene analysis, etc. The numeric solvers used to compute these acoustic properties are too slow for interactive applications. We present a novel geometric deep learning algorithm based on discrete-laplacian and implicit encoders to compute these characteristics for rigid or deformable objects at interactive rates. We use a point cloud approximation of each object, and each point is encoded in a high-dimensional latent space. Our multi-layer network can accurately estimate these acoustic properties for arbitrary topologies and takes less than 1ms per object on a NVIDIA GeForce RTX 2080 Ti GPU. We also prove that our learning method is permutation and rotation invariant and demonstrate high accuracy on objects that are quite different from the training data. We highlight its application to generating environmental acoustic effects in dynamic environments.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We use a novel neural network to efficiently predict the acoustic scattering effect from 3D objects.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=NtCbooyMMb