Depth-map completion for large indoor scene reconstruction. (March 2020)

• Record Type: Journal Article
• Authors: Liu, Hongmin; Tang, Xincheng; Shen, Shuhan
• Is Part Of: Pattern recognition. Volume 99(2020:Mar.)
• Publication Date: 2020-03
• Subjects: Depth completion -- MVS -- 3D Reconstruction -- Point cloud,; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.107112
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Propose a new depth completion algorithm for MVS depth-maps. Use occlusion boundary to solve depth discontinuity problem. Propose an iterative filtering and completion method for large indoor scene reconstruction. Abstract: Traditional Multi View Stereo (MVS) algorithms are often difficult to deal with large-scale indoor scene reconstruction, due to the photo-consistency measurement errors in weak textured regions, which are commonly exist in indoor scenes. To solve this limitation, in this paper we proposed a point cloud completion strategy that combines learning-based depth-map completion and geometry-based consistency filtering to fill large-area missing in depth-maps. The proposed method takes nonuniform and noisy MVS depth-map as input, and completes each depth-map individually. In the completion process, we first complete depth-maps using learning based method, and then filter each depth-map using depth consistency validation with its neighboring depth-maps. This depth-map completion and geometric filtering steps are performed iteratively until the number of depth points is converged. Experiments on large-scale indoor scenes and benchmark MVS datasets demonstrate the effectiveness of the proposed methods.