Survey on differential estimators for 3d point clouds - dataset

Dataset of the survey: Arnal--Anger, L., Lejemble, T., Coeurjolly, D., Barthe, L., & Mellado, N. (2026). Survey on differential estimators for 3d point clouds. In Computer Graphics Forum (Vol. 45, No. 2). [Project page], [Hal link], [doi], [code] Abstract: Recent advancements in 3D scanning technologies, including LiDAR and photogrammetry, have enabled the precise digital replication of real-world objects. These methods are widely used in fields such as GIS, robotics, and cultural heritage. However, the point clouds generated by such scans are often noisy and unstructured, posing challenges for traditional geometry processing tasks. Accurately estimating differential properties like surface curvatures and normals is crucial for tasks such as shape matching and classification, but remains complex due to these inherent challenges.This paper reviews state-of-the-art methods for estimating differential properties from 3D point clouds, with a focus on approaches that offer strong mathematical foundations and theoretical guarantees. We also benchmark these methods using various datasets, evaluating their performance in terms of accuracy, robustness, and efficiency. Our contributions include the release of datasets, tools, and code to promote reproducibility and support future research in this area.调查数据集： Arnal--Anger, L.、Lejemble, T.、Coeurjolly, D.、Barthe, L.与Mellado, N.（2026）。《三维点云微分估计综述》，刊载于《计算机图形学论坛（Computer Graphics Forum）》第45卷第2期。 [项目页面]、[Hal链接]、[DOI]、[代码] 摘要： 近年来，包括激光雷达(LiDAR)和摄影测量在内的三维扫描技术取得了长足进展，实现了真实物体的高精度数字化复刻。此类方法已广泛应用于地理信息系统(GIS)、机器人学以及文化遗产保护等领域。然而，此类扫描生成的三维点云(3D point clouds)往往存在噪声且结构非结构化，给传统几何处理任务带来了诸多挑战。准确估计曲面曲率、法向量等微分属性，对形状匹配与分类等任务至关重要，但受限于上述固有难点，该问题仍具备较高复杂度。 本文综述了当前从三维点云中估计微分属性的前沿方法，重点关注具备扎实数学基础与理论保障的研究路径。此外，本文还依托多组数据集对这些方法开展了基准测试，从精度、鲁棒性与运行效率三个维度评估其性能。本研究的贡献包括公开数据集、工具与代码，以推动该领域的可复现性研究，并为后续相关研究提供支撑。