用於幾何準確輻射場的二維高斯散點化

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 高斯飄點（3D Gaussian Splatting，3DGS）已經徹底改變了輝度場重建的方法，實現了高質量的新視角合成和快速渲染速度，無需預先烘焙。然而，由於 3D 高斯飄點存在多視角不一致的特性，無法準確表示表面。我們提出了2D 高斯飄點（2D Gaussian Splatting，2DGS），這是一種新方法，可以從多視角圖像中建模和重建幾何準確的輝度場。我們的關鍵思想是將 3D 体積折疊成一組2D定向平面高斯盤。與 3D 高斯相比，2D 高斯在建模表面時提供了視角一致的幾何，並具有固有的表面建模能力。為了準確恢復薄表面並實現穩定的優化，我們引入了一個透視準確的2D飄點過程，利用射線-飄點交集和光柵化。此外，我們還結合深度失真和法向一致性項，進一步提高重建的質量。我們展示了我們的可微渲染器可以實現無噪聲和詳細的幾何重建，同時保持競爭力的外觀質量、快速訓練速度和實時渲染。我們的代碼將公開提供。

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.