This paper presents GIR, a 3D Gaussian Inverse Rendering method for relightable scene factorization. Compared to existing methods leveraging discrete meshes or neural implicit fields for inverse rendering, our method utilizes 3D Gaussians to estimate the material properties, illumination, and geometry of an object from multi-view images. Our study is motivated by the evidence showing that 3D Gaussian is a more promising backbone than neural fields in terms of performance, versatility, and efficiency. In this paper, we aim to answer the question: ``How can 3D Gaussian be applied to improve the performance of inverse rendering?'' To address the complexity of estimating normals based on discrete and often in-homogeneous distributed 3D Gaussian representations, we proposed an efficient self-regularization method that facilitates the modeling of surface normals without the need for additional supervision. To reconstruct indirect illumination, we propose an approach that simulates ray tracing. Extensive experiments demonstrate our proposed GIR's superior performance over existing methods across multiple tasks on a variety of widely used datasets in inverse rendering. This substantiates its efficacy and broad applicability, highlighting its potential as an influential tool in relighting and reconstruction. Project page: https://3dgir.github.io

翻译：本文提出GIR，一种基于三维高斯逆渲染的可重光照场景分解方法。相较于现有利用离散网格或神经隐式场进行逆渲染的方法，本方法采用三维高斯从多视角图像中估计物体的材质属性、光照与几何结构。研究表明，三维高斯在性能、通用性与效率方面均优于神经场作为主干网络。本文旨在回答："如何利用三维高斯提升逆渲染性能？" 针对基于离散且非均匀分布的三维高斯表示估算法向量的复杂性，我们提出一种高效的自正则化方法，无需额外监督即可建立表面法向量的建模。为重建间接光照，我们提出一种模拟光线追踪的技术。大量实验表明，在逆渲染领域的多个广泛使用的数据集上，所提出的GIR方法在多任务中的表现均优于现有方法。这证实了其有效性与广泛适用性，凸显了其在重光照与重建领域作为重要工具的潜力。项目页面：https://3dgir.github.io