3D Gaussian Splatting with Normal Information for Mesh Extraction and Improved Rendering
This incremental improvement addresses geometry reconstruction issues for applications in video generation, animation, AR-VR, and gaming.
The paper tackles the problem of imprecise geometry and mesh extraction in 3D Gaussian splatting by introducing a regularization method using signed distance function gradients, resulting in improved rendering quality and mesh reconstruction as shown on datasets like Mip-NeRF360.
Differentiable 3D Gaussian splatting has emerged as an efficient and flexible rendering technique for representing complex scenes from a collection of 2D views and enabling high-quality real-time novel-view synthesis. However, its reliance on photometric losses can lead to imprecisely reconstructed geometry and extracted meshes, especially in regions with high curvature or fine detail. We propose a novel regularization method using the gradients of a signed distance function estimated from the Gaussians, to improve the quality of rendering while also extracting a surface mesh. The regularizing normal supervision facilitates better rendering and mesh reconstruction, which is crucial for downstream applications in video generation, animation, AR-VR and gaming. We demonstrate the effectiveness of our approach on datasets such as Mip-NeRF360, Tanks and Temples, and Deep-Blending. Our method scores higher on photorealism metrics compared to other mesh extracting rendering methods without compromising mesh quality.