Acoustic Volume Rendering for Neural Impulse Response Fields

TL;DR

This paper introduces Acoustic Volume Rendering (AVR), a novel method for modeling acoustic impulse responses using volume rendering techniques, achieving state-of-the-art synthesis quality and supporting realistic acoustic simulations.

Contribution

We adapt volume rendering to model impulse responses in the acoustic domain, introducing frequency-domain rendering and spherical integration for improved accuracy.

Findings

AVR outperforms existing methods in impulse response synthesis.

The approach encodes wave propagation principles inherently.

Developed AcoustiX for more accurate acoustic simulations.

Abstract

Realistic audio synthesis that captures accurate acoustic phenomena is essential for creating immersive experiences in virtual and augmented reality. Synthesizing the sound received at any position relies on the estimation of impulse response (IR), which characterizes how sound propagates in one scene along different paths before arriving at the listener's position. In this paper, we present Acoustic Volume Rendering (AVR), a novel approach that adapts volume rendering techniques to model acoustic impulse responses. While volume rendering has been successful in modeling radiance fields for images and neural scene representations, IRs present unique challenges as time-series signals. To address these challenges, we introduce frequency-domain volume rendering and use spherical integration to fit the IR measurements. Our method constructs an impulse response field that inherently encodes wave propagation principles and achieves state-of-the-art performance in synthesizing impulse responses for novel poses. Experiments show that AVR surpasses current leading methods by a substantial margin. Additionally, we develop an acoustic simulation platform, AcoustiX, which provides more accurate and realistic IR simulations than existing simulators. Code for AVR and AcoustiX are available at https://zitonglan.github.io/avr.