Journal
PATTERN RECOGNITION
Volume 99, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2019.107112
Keywords
Depth completion; MVS; 3D Reconstruction; Point cloud
Funding
- Natural Science Foundation of China [61632003, 61873265, 61572173]
- Henan Science and Technology Innovation Outstanding Youth Program [184100510009]
- Henan University Scientific and Technological Innovation Team Support Program [19IRTSTHN012]
- Fundamental Research Funds for the Universities of Henan Province [NS-FRF1604]
Ask authors/readers for more resources
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. (C) 2019 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available