2D-SuGaR：面向表面的高斯点散布用于几何准确的网格重建
2D-SuGaR: Surface-Aware Gaussian Splatting for Geometrically Accurate Mesh Reconstruction
AI总结：
本文提出2D-SuGaR方法，通过结合单目深度和法线先验，提升多视图图像中网格重建的几何精度和鲁棒性，实现在DTU数据集上达到最先进的重建效果。
摘要：
3D高斯点散布（3DGS）已发展为一种强大的技术，用于实时生成逼真的场景渲染。然而，3DGS的体积性质限制了其准确捕捉表面几何的能力。为此，提出了2D高斯点散布（2DGS）以实现从多视角图像中一致且几何准确的表面重建。然而，2DGS对高斯原始体的初始化敏感。依赖结构从运动（SfM）初始化，在挑战性图像集上可能产生较差的估计，导致次优结果。在本文中，我们通过引入单目深度和法线先验来增强2DGS，提高几何精度和鲁棒性。我们提出了一种基于深度的初始化策略用于高斯点，并引入基于聚类的技巧来修剪退化高斯点。我们在DTU数据集上评估了我们的方法，其中它在网格重建中实现了最先进的结果，同时保持高质量的视点合成。
英文摘要：
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for generating photorealistic renderings of a scene in real-time. However, the volumetric nature of 3DGS limits its ability to accurately capture surface geometry. To address this, 2D Gaussian Splatting (2DGS) was proposed to enable view-consistent and geometrically accurate surface reconstruction from multi-view images. However, 2DGS can be sensitive to the initialization of the Gaussian primitives. Reliance on Structure-from-Motion (SfM) initializations, which can produce poor estimates on challenging image sets, may lead to subpar results. In this work, we enhance 2DGS by incorporating monocular depth and normal priors to improve both geometric accuracy and robustness. We propose a depth-guided initialization strategy for Gaussians and introduce a clustering-based technique for pruning degenerate Gaussians. We evaluate our method on the DTU dataset, where it achieves state-of-the-art results in mesh reconstruction while preserving high-quality novel view synthesis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
