PRTGaussian: Efficient Relighting Using 3D Gaussians with Precomputed Radiance Transfer

TL;DR

PRTGaussian introduces a real-time relightable view synthesis method combining 3D Gaussians and Precomputed Radiance Transfer, enabling efficient and high-quality relighting of objects from multi-view data.

Contribution

It is the first to integrate 3D Gaussians with PRT for real-time relightable view synthesis from multi-view images.

Findings

Achieves real-time relighting with high visual quality.

Balances detailed relighting effects and computational efficiency.

Demonstrates effectiveness on synthetic datasets.

Abstract

We present PRTGaussian, a realtime relightable novel-view synthesis method made possible by combining 3D Gaussians and Precomputed Radiance Transfer (PRT). By fitting relightable Gaussians to multi-view OLAT data, our method enables real-time, free-viewpoint relighting. By estimating the radiance transfer based on high-order spherical harmonics, we achieve a balance between capturing detailed relighting effects and maintaining computational efficiency. We utilize a two-stage process: in the first stage, we reconstruct a coarse geometry of the object from multi-view images. In the second stage, we initialize 3D Gaussians with the obtained point cloud, then simultaneously refine the coarse geometry and learn the light transport for each Gaussian. Extensive experiments on synthetic datasets show that our approach can achieve fast and high-quality relighting for general objects. Code and data are available at https://github.com/zhanglbthu/PRTGaussian.