用法向量引导深度传播，提升稀疏视角下的三维表面重建质量
Sparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal Priors
- 基于法向量先验传播高置信度深度信息，填补低置信区域
- 提出边缘感知正则化，缓解高斯点离散导致的深度不连续
- 在DTU和Tanks-and-Temples数据集上优于现有方法
从稀疏视角进行3D重建是计算机视觉中的挑战性任务。尽管近期基于3D高斯点阵（3DGS）的方法在新视角合成中取得了显著成果，但利用稀疏视角重建高质量几何表面仍面临困难，主要源于几何线索不足以及高斯点的离散特性。本文提出一种基于3DGS的新型高保真表面重建方法。核心思想是引入法向量引导的深度传播策略，将高置信度区域的深度信息扩展至低置信区域以约束深度分布。同时，设计了异常深度边缘感知正则化，有效缓解由高斯点离散性引起的深度不连续问题。在DTU和Tanks-and-Temples数据集上的大量实验表明，该方法在稀疏视图表面重建任务中优于当前最优方法。
原文摘要 · Abstract (English)
3D reconstruction from sparse views is a challenging task in 3D computer vision. Recent studies on 3D Gaussian Splatting (3DGS) have achieved remarkable results with sparse views in novel view synthesis, yet reconstructing high-quality geometric surfaces from sparse views remains a challenge, due to the limited geometry clues and the discreteness of Gaussians. In this paper, we propose a novel 3DGS-based method for high-fidelity surface reconstruction from sparse views. Our key insight is to introduce a normal-guided depth propagation approach, which can extend depth information from high-confidence regions to constrain the depth in low-confidence areas. Additionally, we propose an abnormal depth edge-aware regularization to address depth discontinuities caused by the discreteness of Gaussians. Extensive experiments on DTU and Tanks-and-Temples datasets demonstrate that our method outperforms the state-of-the-art methods in sparse view surface reconstruction. Project page: https://hanl2010.github.io/DP-GS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。