Please use this identifier to cite or link to this item:
|Title:||Iterative poisson surface reconstruction (iPSR) for unoriented points||Authors:||Hou, Fei
|Keywords:||Computer Science - Graphics||Issue Date:||2022||Source:||Hou, F., Wang, C., Wang, W., Qin, H., Qian, C. & He, Y. (2022). Iterative poisson surface reconstruction (iPSR) for unoriented points. ACM Transactions On Graphics, 41(4), 128-. https://dx.doi.org/10.1145/3528223.3530096||Project:||MOE-T2EP20220-0005
|Journal:||ACM Transactions on Graphics||Abstract:||Poisson surface reconstruction (PSR) remains a popular technique for reconstructing watertight surfaces from 3D point samples thanks to its efficiency, simplicity, and robustness. Yet, the existing PSR method and subsequent variants work only for oriented points. This paper intends to validate that an improved PSR, called iPSR, can completely eliminate the requirement of point normals and proceed in an iterative manner. In each iteration, iPSR takes as input point samples with normals directly computed from the surface obtained in the preceding iteration, and then generates a new surface with better quality. Extensive quantitative evaluation confirms that the new iPSR algorithm converges in 5-30 iterations even with randomly initialized normals. If initialized with a simple visibility based heuristic, iPSR can further reduce the number of iterations. We conduct comprehensive comparisons with PSR and other powerful implicit-function based methods. Finally, we confirm iPSR's effectiveness and scalability on the AIM@SHAPE dataset and challenging (indoor and outdoor) scenes. Code and data for this paper are at https://github.com/houfei0801/ipsr.||URI:||https://hdl.handle.net/10356/163337||ISSN:||0730-0301||DOI:||10.1145/3528223.3530096||Rights:||© 2022 The owner/author(s). All rights reserved.||Fulltext Permission:||none||Fulltext Availability:||No Fulltext|
|Appears in Collections:||SCSE Journal Articles|
Updated on Feb 7, 2023
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.