SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

TL;DR

SuGaR introduces a fast, surface-aligned Gaussian Splatting method for efficient 3D mesh extraction and high-quality rendering, enabling quick editing and manipulation of complex scenes.

Contribution

The paper presents a novel regularization and mesh extraction technique from Gaussian Splatting, significantly improving speed and quality over existing neural SDF methods.

Findings

Mesh extraction is achieved in minutes, much faster than hours with neural SDFs.

The method preserves scene details and improves rendering quality.

Enables easy editing and manipulation of 3D scenes using traditional software.

Abstract

We propose a method to allow precise and extremely fast mesh extraction from 3D Gaussian Splatting. Gaussian Splatting has recently become very popular as it yields realistic rendering while being significantly faster to train than NeRFs. It is however challenging to extract a mesh from the millions of tiny 3D gaussians as these gaussians tend to be unorganized after optimization and no method has been proposed so far. Our first key contribution is a regularization term that encourages the gaussians to align well with the surface of the scene. We then introduce a method that exploits this alignment to extract a mesh from the Gaussians using Poisson reconstruction, which is fast, scalable, and preserves details, in contrast to the Marching Cubes algorithm usually applied to extract meshes from Neural SDFs. Finally, we introduce an optional refinement strategy that binds gaussians to the surface of the mesh, and jointly optimizes these Gaussians and the mesh through Gaussian splatting rendering. This enables easy editing, sculpting, rigging, animating, compositing and relighting of the Gaussians using traditional softwares by manipulating the mesh instead of the gaussians themselves. Retrieving such an editable mesh for realistic rendering is done within minutes with our method, compared to hours with the state-of-the-art methods on neural SDFs, while providing a better rendering quality. Our project page is the following: https://anttwo.github.io/sugar/