RaDe-GS: Rasterizing Depth in Gaussian Splatting
This work addresses shape reconstruction accuracy for 3D modeling applications, representing an incremental improvement by enhancing existing Gaussian Splatting methods.
The paper tackles the problem of limited shape accuracy in Gaussian Splatting for 3D reconstruction by introducing a rasterized approach to render depth and surface normal maps, achieving a Chamfer distance error comparable to NeuraLangelo on the DTU dataset while maintaining computational efficiency.
Gaussian Splatting (GS) has proven to be highly effective in novel view synthesis, achieving high-quality and real-time rendering. However, its potential for reconstructing detailed 3D shapes has not been fully explored. Existing methods often suffer from limited shape accuracy due to the discrete and unstructured nature of Gaussian splats, which complicates the shape extraction. While recent techniques like 2D GS have attempted to improve shape reconstruction, they often reformulate the Gaussian primitives in ways that reduce both rendering quality and computational efficiency. To address these problems, our work introduces a rasterized approach to render the depth maps and surface normal maps of general 3D Gaussian splats. Our method not only significantly enhances shape reconstruction accuracy but also maintains the computational efficiency intrinsic to Gaussian Splatting. It achieves a Chamfer distance error comparable to NeuraLangelo on the DTU dataset and maintains similar computational efficiency as the original 3D GS methods. Our method is a significant advancement in Gaussian Splatting and can be directly integrated into existing Gaussian Splatting-based methods.