Fast and Accurate Normal Estimation for Point Clouds Via Patch Stitching. (January 2022)

• Record Type: Journal Article
• Authors: Zhou, Jun; Jin, Wei; Wang, Mingjie; Liu, Xiuping; Li, Zhiyang; Liu, Zhaobin
• Is Part Of: Computer aided design. Volume 142(2022)
• Publication Date: 2022-01
• Subjects: Normal estimation -- Point cloud processing -- Patch stitching -- Multi-branch planar experts -- Adaptive local feature aggregation; 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.2021.103121
• Languages: English
• ISSNs: 0010-4485

Abstract

Abstract: This paper presents an effective normal estimation method adopting multi-patch stitching for an unstructured point cloud. The majority of learning-based approaches encode a local patch around each point of a whole model and estimate the normals in a point-by-point manner. In contrast, we suggest a more efficient pipeline, in which we introduce a patch-level normal estimation architecture to process a series of overlapping patches. Additionally, a multi-normal selection method based on weights, dubbed as multi-patch stitching, integrates the normals from the overlapping patches. To reduce the adverse effects of sharp corners or noise in a patch, we introduce an adaptive local feature aggregation layer to focus on an anisotropic neighborhood. We then utilize a multi-branch planar experts module to break the mutual influence between underlying piecewise surfaces in a patch. At the stitching stage, we use the learned weights of multi-branch planar experts and distance weights between points to select the best normal from the overlapping parts. Furthermore, we put forward constructing a sparse matrix representation to reduce large-scale retrieval overheads for the loop iterations dramatically. Extensive experiments demonstrate that our method achieves SOTA results with the advantage of lower computational costs and higher robustness to noise over most existed approaches. Highlights: A flexible and fast multi-patch stitching framework is proposed, and the network's time complexity can be reduced. A sparse index matrix is introduced to speed up the process that maps the point IDs of patches to the point cloud. A multi-branch planar experts module and an adaptive local feature aggregation layer are introduced.