GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction
This work addresses the problem of surface reconstruction in 3D computer vision for applications like novel view synthesis, offering an incremental improvement over existing methods.
The paper tackled the challenge of reconstructing high-quality surfaces with fine details using 3D Gaussian Splatting by introducing GausSurf, which uses geometry guidance from multi-view consistency in texture-rich areas and normal priors in texture-less areas, resulting in improved reconstruction quality and faster computation time compared to state-of-the-art methods on DTU and Tanks and Temples datasets.
3D Gaussian Splatting has achieved impressive performance in novel view synthesis with real-time rendering capabilities. However, reconstructing high-quality surfaces with fine details using 3D Gaussians remains a challenging task. In this work, we introduce GausSurf, a novel approach to high-quality surface reconstruction by employing geometry guidance from multi-view consistency in texture-rich areas and normal priors in texture-less areas of a scene. We observe that a scene can be mainly divided into two primary regions: 1) texture-rich and 2) texture-less areas. To enforce multi-view consistency at texture-rich areas, we enhance the reconstruction quality by incorporating a traditional patch-match based Multi-View Stereo (MVS) approach to guide the geometry optimization in an iterative scheme. This scheme allows for mutual reinforcement between the optimization of Gaussians and patch-match refinement, which significantly improves the reconstruction results and accelerates the training process. Meanwhile, for the texture-less areas, we leverage normal priors from a pre-trained normal estimation model to guide optimization. Extensive experiments on the DTU and Tanks and Temples datasets demonstrate that our method surpasses state-of-the-art methods in terms of reconstruction quality and computation time.