GS^3: Efficient Relighting with Triple Gaussian Splatting

TL;DR

This paper introduces GS^3, a novel Gaussian-based representation and triple splatting method enabling real-time, high-quality relighting and view synthesis from multi-view images, with efficient training and rendering on standard hardware.

Contribution

It proposes a new spatial and angular Gaussian representation with triple splatting for fast, high-quality relighting and view synthesis, outperforming existing methods in speed and quality.

Findings

Achieves 90 fps rendering speed on a single GPU.

Demonstrates high-quality results across diverse geometries and appearances.

Training time is reduced to 40-70 minutes.

Abstract

We present a spatial and angular Gaussian based representation and a triple splatting process, for real-time, high-quality novel lighting-and-view synthesis from multi-view point-lit input images. To describe complex appearance, we employ a Lambertian plus a mixture of angular Gaussians as an effective reflectance function for each spatial Gaussian. To generate self-shadow, we splat all spatial Gaussians towards the light source to obtain shadow values, which are further refined by a small multi-layer perceptron. To compensate for other effects like global illumination, another network is trained to compute and add a per-spatial-Gaussian RGB tuple. The effectiveness of our representation is demonstrated on 30 samples with a wide variation in geometry (from solid to fluffy) and appearance (from translucent to anisotropic), as well as using different forms of input data, including rendered images of synthetic/reconstructed objects, photographs captured with a handheld camera and a flash, or from a professional lightstage. We achieve a training time of 40-70 minutes and a rendering speed of 90 fps on a single commodity GPU. Our results compare favorably with state-of-the-art techniques in terms of quality/performance. Our code and data are publicly available at https://GSrelight.github.io/.