Modeling and Driving Human Body Soundfields through Acoustic Primitives

TL;DR

This paper introduces a novel framework for high-quality, real-time spatial audio rendering of full 3D human body soundfields using acoustic primitives, enhancing near-field accuracy and efficiency.

Contribution

It presents a new acoustic primitive-based approach for efficient, accurate near-field spatial audio rendering of human body soundscapes from basic visual and audio inputs.

Findings

Achieves high-quality 3D soundfield rendering including speech and interactions.

Enables real-time near-field audio rendering with smaller representations.

Outperforms previous methods in accuracy and efficiency.

Abstract

While rendering and animation of photorealistic 3D human body models have matured and reached an impressive quality over the past years, modeling the spatial audio associated with such full body models has been largely ignored so far. In this work, we present a framework that allows for high-quality spatial audio generation, capable of rendering the full 3D soundfield generated by a human body, including speech, footsteps, hand-body interactions, and others. Given a basic audio-visual representation of the body in form of 3D body pose and audio from a head-mounted microphone, we demonstrate that we can render the full acoustic scene at any point in 3D space efficiently and accurately. To enable near-field and realtime rendering of sound, we borrow the idea of volumetric primitives from graphical neural rendering and transfer them into the acoustic domain. Our acoustic primitives result in an order of magnitude smaller soundfield representations and overcome deficiencies in near-field rendering compared to previous approaches.