GSCache: Real-Time Radiance Caching for Volume Path Tracing using 3D Gaussian Splatting

TL;DR

This paper introduces GSCache, a real-time radiance caching method for volume path tracing that uses 3D Gaussian splatting to improve rendering quality and efficiency in scientific visualization.

Contribution

It presents a novel, trainable radiance cache based on 3D Gaussian splatting that adapts dynamically to scene changes, enhancing volume rendering quality without extra computational costs.

Findings

Achieves less noisy, higher-quality images in volume rendering.

Maintains comparable rendering costs to baseline methods.

Outperforms state-of-the-art neural radiance caching in tests.

Abstract

Real-time path tracing is rapidly becoming the standard for rendering in entertainment and professional applications. In scientific visualization, volume rendering plays a crucial role in helping researchers analyze and interpret complex 3D data. Recently, photorealistic rendering techniques have gained popularity in scientific visualization, yet they face significant challenges. One of the most prominent issues is slow rendering performance and high pixel variance caused by Monte Carlo integration. In this work, we introduce a novel radiance caching approach for path-traced volume rendering. Our method leverages advances in volumetric scene representation and adapts 3D Gaussian splatting to function as a multi-level, path-space radiance cache. This cache is designed to be trainable on the fly, dynamically adapting to changes in scene parameters such as lighting configurations and transfer functions. By incorporating our cache, we achieve less noisy, higher-quality images without increasing rendering costs. To evaluate our approach, we compare it against a baseline path tracer that supports uniform sampling and next-event estimation and the state-of-the-art for neural radiance caching. Through both quantitative and qualitative analyses, we demonstrate that our path-space radiance cache is a robust solution that is easy to integrate and significantly enhances the rendering quality of volumetric visualization applications while maintaining comparable computational efficiency.