发表机构
KakaoMobility（Kakao出行）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对3DGS在复杂场景中的几何失真问题，提出融合表面法线与密集深度先验的正则化方法，提升几何精度与视觉质量，并在街景及高反射环境验证了鲁棒性。
AI 中文摘要
三维高斯泼溅（3D Gaussian Splatting, 3DGS）是一种用于三维场景渲染的最先进技术，具有高效率和出色的视觉质量。然而，由于3DGS依赖于从运动恢复结构（Structure-from-Motion, SfM）获得的初始稀疏点集以及视角相关属性，它可能遭受几何不准确和视觉伪影，尤其是在复杂场景中。为解决这些挑战，我们提出了一种改进的3DGS方法，通过整合几何先验（包括表面法线和密集深度信息）来正则化优化过程。表面法线正则化通过将高斯协方差与局部表面结构对齐来提高几何一致性，而密集深度先验结合SfM的初始点增强了逐像素深度估计，提高了准确性并减少了模糊性。这些增强使得方法能够稳健地处理多样且复杂的现实世界场景，最小化视觉失真并提高各种环境下的重建质量。为验证我们的方法，我们在具有挑战性的数据集上进行了评估，包括街景场景和高反射环境，并在多个SfM流程上进行了测试。我们的结果证明了方法在不同环境中的兼容性，并突出了其稳健性。实验发现进一步表明，我们的方法提高了几何准确性和视觉质量，为复杂环境中的实时三维场景渲染建立了一个可靠的解决方案。
英文摘要
3D Gaussian Splatting (3DGS) is a state-of-the-art technique for 3D scene rendering, offering high efficiency and excellent visual quality. However, because 3DGS relies on an initial sparse point set from Structure-from-Motion (SfM) and view-dependent properties, it can suffer from geometric inaccuracies and visual artifacts, particularly in complex scenes. To address these challenges, we propose an improved 3DGS approach that regularizes the optimization process by integrating geometric priors, including surface normals and dense depth information. Surface normal regularization improves geometric consistency by aligning Gaussian covariance with local surface structures, while dense depth priors combined with an initial points from SfM enhance per-pixel depth estimation, increasing accuracy and reducing ambiguities. These enhancements enable robust handling of diverse and complex real-world scenarios, minimizing visual distortions and improving reconstruction quality across various environments. To validate our method, we evaluate it on challenging datasets, including street-view scenes and highly reflective environments, while testing it across multiple SfM pipelines. Our results demonstrate compatibility across diverse environments and highlight the robustness of our approach. Experimental findings further show that our method enhances geometric accuracy and visual quality, establishing a reliable solution for real-time 3D scene rendering in complex environments.
Comments7 pages, 2 figures, 1 table. Oral presentation at ISPRS Geospatial Week 2025 (Dubai). Project page: https://gandanlee.github.io/pdigs/ Code: https://github.com/gandanlee/pdigs
Journal refInt. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-G-2025, 891-897, 2025
DOI：10.5194/isprs-archives-XLVIII-G-2025-891-2025
