Deep Point Cloud Normal Estimation via Triplet Learning

arXiv:2110.10494v2 Announce Type: replace
Abstract: 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 …

abstract accuracy arxiv cloud cs.cg cs.cv cs.gr current features graphics noise normal novel paper robustness show type via vision