用于几何精确辐射场的二维高斯喷洒

2D Gaussian Splatting for Geometrically Accurate Radiance Fields

March 26, 2024

作者: Binbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger, Shenghua Gao

cs.AI

摘要

最近，3D 高斯飘逸（3D Gaussian Splatting，3DGS）彻底改变了辐射场重建，实现了高质量的新视角合成和快速渲染速度，无需预先计算。然而，由于 3D 高斯函数的多视角不一致性，3DGS 无法准确表示表面。我们提出了2D 高斯飘逸（2D Gaussian Splatting，2DGS），这是一种新颖的方法，可以从多视角图像中对几何精确的辐射场进行建模和重建。我们的关键思想是将 3D 体积折叠成一组2D定向平面高斯盘。与 3D 高斯函数不同，2D 高斯函数提供了视角一致的几何形状，同时固有地对表面进行建模。为了准确恢复薄表面并实现稳定的优化，我们引入了透视准确的2D飘逸过程，利用射线-飘逸相交和光栅化。此外，我们还结合深度失真和法线一致性项，进一步提高了重建质量。我们展示了我们的可微渲染器能够实现无噪声和详细几何重建，同时保持竞争力的外观质量、快速训练速度和实时渲染。我们的代码将公开发布。

English

3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking. However, 3DGS fails to accurately represent surfaces due to the multi-view inconsistent nature of 3D Gaussians. We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images. Our key idea is to collapse the 3D volume into a set of 2D oriented planar Gaussian disks. Unlike 3D Gaussians, 2D Gaussians provide view-consistent geometry while modeling surfaces intrinsically. To accurately recover thin surfaces and achieve stable optimization, we introduce a perspective-accurate 2D splatting process utilizing ray-splat intersection and rasterization. Additionally, we incorporate depth distortion and normal consistency terms to further enhance the quality of the reconstructions. We demonstrate that our differentiable renderer allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering. Our code will be made publicly available.