arXiv 2405.196712025-04-01cs.CV

GaussianRoom：利用 SDF 引导和单目线索改进 3D Gaussian Splatting 以实现室内场景重建

GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstruction

Tsinghua University（清华大学）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；University of Science and Technology of China（中国科学技术大学）

Haodong Xiang, Xinghui Li, Kai Cheng, Xiansong Lai, Wanting Zhang, Zhichao Liao, Long Zeng, Xueping Liu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对3DGS在室内无纹理区域重建不完整的问题，提出融合神经SDF与3DGS的统一优化框架，利用SDF引导高斯致密化与剪枝，并引入法线和边缘先验正则化，在表面重建和新视角合成上达到SOTA。

摘要：

具身智能需要精确的重建和渲染来模拟大规模真实世界数据。尽管 3D Gaussian Splatting (3DGS) 最近展示了高质量和实时性能的结果，但在具有大面积无纹理区域的室内场景中仍面临挑战，由于点云初始化不良和优化约束不足，导致重建不完整且带有噪声。受符号距离场 (SDF) 连续性的启发，SDF 在表面建模方面具有天然优势，我们提出了一个将神经符号距离场 (SDF) 与 3DGS 集成的统一优化框架，以实现精确的几何重建和实时渲染。该框架引入神经 SDF 场来引导 Gaussians 的致密化和剪枝，使 Gaussians 即使在点云初始化较差时也能准确建模场景。同时，由 Gaussians 表示的几何结构通过引导其点采样来提高 SDF 场的效率。此外，我们引入了两个基于法线和边缘先验的正则化项，以解决无纹理区域的几何歧义并提高细节准确性。在 ScanNet 和 ScanNet++ 上的大量实验表明，我们的方法在表面重建和新视角合成方面均达到了最先进的性能。

英文摘要：

Embodied intelligence requires precise reconstruction and rendering to simulate large-scale real-world data. Although 3D Gaussian Splatting (3DGS) has recently demonstrated high-quality results with real-time performance, it still faces challenges in indoor scenes with large, textureless regions, resulting in incomplete and noisy reconstructions due to poor point cloud initialization and underconstrained optimization. Inspired by the continuity of signed distance field (SDF), which naturally has advantages in modeling surfaces, we propose a unified optimization framework that integrates neural signed distance fields (SDFs) with 3DGS for accurate geometry reconstruction and real-time rendering. This framework incorporates a neural SDF field to guide the densification and pruning of Gaussians, enabling Gaussians to model scenes accurately even with poor initialized point clouds. Simultaneously, the geometry represented by Gaussians improves the efficiency of the SDF field by piloting its point sampling. Additionally, we introduce two regularization terms based on normal and edge priors to resolve geometric ambiguities in textureless areas and enhance detail accuracy. Extensive experiments in ScanNet and ScanNet++ show that our method achieves state-of-the-art performance in both surface reconstruction and 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。