Detecting sharp features in raw 3D point clouds is an essential step for designing efficient priors in several 3D Vision applications. This paper presents a deep learning-based approach that learns to detect and consolidate sharp feature points on raw 3D point clouds. We devise a multi-task neural network architecture that identifies points near sharp features and predicts displacement vectors toward the local sharp features. The so-detected points are thus consolidated via relocation. Our approach is robust against noise by utilizing a dynamic labeling oracle during the training phase. The approach is also flexible and can be combined with several popular point-based network architectures. Our experiments demonstrate that our approach outperforms the previous work in terms of detection accuracy measured on the popular ABC dataset. We show the efficacy of the proposed approach by applying it to several 3D vision tasks.

检测原始 3D 点云中的锐利特征是在多个 3D Vision 应用程序中设计高效先验的重要步骤。本文介绍了一种基于深度学习的方法，该方法学习检测和整合原始 3D 点云上的尖锐特征点。我们设计了一种多任务神经网络架构，可以识别靠近尖锐特征的点并预测朝向局部尖锐特征的位移向量。如此检测到的点因此通过重定位被合并。我们的方法通过在训练阶段使用动态标记 oracle 来抵抗噪声。该方法也很灵活，可以与几种流行的基于点的网络架构相结合。我们的实验表明，我们的方法在流行的 ABC 数据集上测量的检测精度方面优于以前的工作。