Geometry Guided Deep Surface Normal Estimation. (January 2022)

• Record Type: Journal Article
• Authors: Zhang, Jie; Cao, Jun-Jie; Zhu, Hai-Rui; Yan, Dong-Ming; Liu, Xiu-Ping
• Is Part Of: Computer aided design. Volume 142(2022)
• Publication Date: 2022-01
• Subjects: Normal estimation -- Unstructured 3D point clouds -- 3D point cloud deep learning; Computer-aided design -- Periodicals; Engineering design -- Data processing -- Periodicals; Computer graphics -- Periodicals; Conception technique -- Informatique -- Périodiques; Infographie -- Périodiques; Computer graphics; Engineering design -- Data processing; Periodicals; Electronic journals; 620.00420285
• DOI: 10.1016/j.cad.2021.103119
• Languages: English
• ISSNs: 0010-4485

Abstract

Abstract: We propose a geometry-guided neural network architecture for robust and detail-preserving surface normal estimation for unstructured point clouds. Previous deep normal estimators usually estimate the normal directly from the neighbors of a query point, which lead to poor performance. The proposed network is composed of a weight learning sub-network (WL-Net) and a lightweight normal learning sub-network (NL-Net). WL-Net first predicates point-wise weights for generating an optimized point set (OPS) from the input. Then, NL-Net estimates a more accurate normal from the OPS especially when the local geometry is complex. To boost the weight learning ability of the WL-Net, we introduce two geometric guidance in the network. First, we design a weight guidance using the deviations between the neighbor points and the ground truth tangent plane of the query point. This deviation guidance offers a "ground truth" for weights corresponding to some reliable inliers and outliers determined by the tangent plane. Second, we integrate the normals of multiple scales into the input. Its performance and robustness are further improved without relying on multi-branch networks, which are employed in previous multi-scale normal estimators. Thus our method is more efficient. Qualitative and quantitative evaluations demonstrate the advantages of our approach over the state-of-the-art methods, in terms of estimation accuracy, model size and inference time. Code is available at https://github.com/2429581027/local-geometric-guided . Highlights: A new two-step normal estimation method. Integrate geometric priors into deep learning framework. Replace multi-scale architecture by multi-scale geometric input. Achieve 10.79 angle error in comparison with the previous state of the art of 11.78.