Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds

Zhao, Wenbin1; Lei, Jiabao1; Wen, Yuxin1; Zhang, Jianguo4; Jia, Kui1,2,3

10.1109/CVPR46437.2021.01012

2021

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

1063-6919

978-1-6654-4510-8

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021

10251-10260

JUN 19-25, 2021

null,null,ELECTR NETWORK

10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA

IEEE COMPUTER SOC

Shape modeling and reconstruction from raw point clouds of objects stand as a fundamental challenge in vision and graphics research. Classical methods consider analytic shape priors; however, their performance is degraded when the scanned points deviate from the ideal conditions of cleanness and completeness. Important progress has been recently made by data-driven approaches, which learn global and/or local models of implicit surface representations from auxiliary sets of training shapes. Motivated from a universal phenomenon that self-similar shape patterns of local surface patches repeat across the entire surface of an object, we aim to push forward the data-driven strategies and propose to learn a local implicit surface network for a shared, adaptive modeling of the entire surface for a direct surface reconstruction from raw point cloud; we also enhance the leveraging of surface self-similarities by improving correlations among the optimized latent codes of individual surface patches. Given that orientations of raw points could be unavailable or noisy, we extend signagnostic learning into our local implicit model, which enables our recovery of signed implicit fields of local surfaces from the unsigned inputs. We term our framework as Sign-Agnostic Implicit Learning of Surface Self-Similarities (SAIL-S3). With a global post-optimization of local sign flipping, SAIL-S3 is able to directly model raw, un-oriented point clouds and reconstruct high-quality object surfaces. Experiments show its superiority over existing methods.

Training Surface reconstruction Computer vision Correlation Codes Adaptive systems Shape

其他

英语

CPCI-S ; EI

National Natural Science Foundation of China[61771201] ; Program for Guangdong Introducing Innovative and Entrepreneurial Teams[2017ZT07X183] ; Guangdong R&D key project of China[2019B010155001]

Computer Science ; Imaging Science & Photographic Technology

Computer Science, Artificial Intelligence ; Imaging Science & Photographic Technology

WOS:000742075000025

20220411509742

Computer vision ; Learning systems

Computer Applications:723.5 ; Vision:741.2

Web of Science

1.South China Univ Technol, Guangzhou, Peoples R China
2.Pazhou Lab, Guangzhou, Peoples R China
3.Peng Cheng Lab, Shenzhen, Peoples R China
4.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Peoples R China

Zhao, Wenbin,Lei, Jiabao,Wen, Yuxin,et al. Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds[C]. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:IEEE COMPUTER SOC,2021:10251-10260.