We present a novel method for reconstructing a 3D implicit surface from a large-scale, sparse, and noisy point cloud. Our approach builds upon the recently introduced Neural Kernel Fields (NKF) representation. It enjoys similar generalization capabilities to NKF, while simultaneously addressing its main limitations: (a) We can scale to large scenes through compactly supported kernel functions, which enable the use of memory-efficient sparse linear solvers. (b) We are robust to noise, through a gradient fitting solve. (c) We minimize training requirements, enabling us to learn from any dataset of dense oriented points, and even mix training data consisting of objects and scenes at different scales. Our method is capable of reconstructing millions of points in a few seconds, and handling very large scenes in an out-of-core fashion. We achieve state-of-the-art results on reconstruction benchmarks consisting of single objects, indoor scenes, and outdoor scenes.

翻译：我们提出了一种从大规模、稀疏且有噪声的点云中重建三维隐式曲面的新方法。该方法基于近期提出的神经核场（NKF）表示，在具备与NKF相似泛化能力的同时，解决了其关键局限性：（a）通过紧支撑核函数，我们能够利用内存高效的稀疏线性求解器处理大规模场景；（b）通过梯度拟合求解实现对噪声的鲁棒性；（c）最小化训练需求，使模型可从任意包含稠密有向点的数据集中学习，甚至能混合训练包含不同尺度物体和场景的数据。该方法可在数秒内重建数百万个点，并以核外（out-of-core）方式处理超大规模场景。在由单一物体、室内场景和室外场景组成的重建基准测试中，我们取得了最先进的成果。