3D-PCGR: Colored Point Cloud Generation and Reconstruction with Surface and Scale Constraints

• Published in: Remote sensing (Basel, Switzerland) Vol. 16; no. 6; p. 1004
• Main Authors: Yuan, Chaofeng, Pan, Jinghui, Zhang, Zhaoxiang, Qi, Min, Xu, Yuelei
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.03.2024
• Subjects: 3-D films; 3D point cloud; Algorithms; Computer graphics; Consistency; Image reconstruction; Methods; Neural networks; object reconstruction; Occlusion; point cloud generation; Semantics; shape completion; Three dimensional models
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs16061004

In the field of 3D point cloud data, the 3D representation of objects is often affected by factors such as lighting, occlusion, and noise, leading to issues of information loss and incompleteness in the collected point cloud data. Point cloud completion algorithms aim to generate complete object point cloud data using partial or local point cloud data as input. Despite promising results achieved by existing methods, current point cloud completion approaches often lack smooth and structural consistency, resulting in a messy overall structure. To address these shortcomings in point cloud completion, we propose a point cloud generative method based on surface consistency and scale rendering. In addition, to solve the limitation of existing methods that mainly focus on geometric features in 3D point cloud completion and do not make full use of color information, we introduce an object reconstruction method based on texture and geometric features. Extensive experiments demonstrate that our proposed methods exhibit superior performance in terms of local details and overall object structure.