Normal estimation on 3D point clouds is a fundamental problem in 3D vision and graphics. Current methods often show limited accuracy in predicting normals at sharp features (e.g., edges and corners) and less robustness to noise. In this paper, we propose a novel normal estimation method for point clouds. It consists of two phases: (a) feature encoding which learns representations of local patches, and (b) normal estimation that takes the learned representation as input and regresses the normal vector. We are motivated that local patches on isotropic and anisotropic surfaces have similar or distinct normals, and that separable features or representations can be learned to facilitate normal estimation. To realise this, we first construct triplets of local patches on 3D point cloud data, and design a triplet network with a triplet loss for feature encoding. We then design a simple network with several MLPs and a loss function to regress the normal vector. Despite having a smaller network size compared to most other methods, experimental results show that our method preserves sharp features and achieves better normal estimation results on CAD-like shapes.
翻译:对 3D 点云的正常估计是 3D 视觉和图形中的一个基本问题。 目前的方法在预测尖锐特征(例如边缘和角)的正常状态时往往显示的准确性有限,而且对噪音的稳健性较低。 在本文中,我们提出了对点云的新的正常估计方法。 它由两个阶段组成:(a) 特性编码,它能了解局部补丁的表示方式,和(b) 通常估计,它能将所学的表示方式作为输入和递减正常矢量。我们的动机是,异形和异地表上的局部补丁具有相似或不同的正常状态,并且可以学习分解特性或表示方式来便利正常估计。为了实现这一点,我们首先在 3D 点云数据上建立局部补丁三重点, 设计三重线网络, 并配有三重显示特性编码的三重损失的三重网络。 然后我们设计一个带有数 MLP 和损失函数的简单网络, 以返回正常矢量。尽管与大多数方法相比网络规模较小,但实验结果显示我们的方法保持精确的特性并取得更好的正常估计结果。