Back to Search
Start Over
Confidence-Based Large-Scale Dense Multi-View Stereo.
- Source :
-
IEEE Transactions on Image Processing . 2020, Vol. 29, p7176-7191. 16p. - Publication Year :
- 2020
-
Abstract
- Albeit remarkable progress has been made to improve the accuracy and completeness of multi-view stereo (MVS), existing methods still suffer from either sparse reconstructions of low-textured surfaces or heavy computational burden. In this paper, we propose a Confidence-based Large-scale Dense Multi-view Stereo (CLD-MVS) method for high resolution imagery. Firstly, we formulate MVS as a multi-view depth estimation problem, and employ a normal-aware efficient PatchMatch stereo to estimate the initial depth and normal map for each reference view. A self-supervised deep learning method is then developed to predict the spatial confidence for multi-view depth maps, which is combined with cross-view consistency to generate the ground control points. Subsequently, a confidence-driven and boundary-aware interpolation scheme using static and dynamic guidance is adopted to synthesize dense depth and normal maps. Finally, a refinement procedure which leverages synthesized depth and normal as prior is conducted to estimate cross-view consistent surface. Experiments show that the proposed CLD-MVS method achieves high geometric completeness while preserving fine-scale details. In particular, it has ranked No. 1 on the ETH3D high-resolution MVS benchmark in terms of $F_{1}$ -score. [ABSTRACT FROM AUTHOR]
- Subjects :
- *SURFACE reconstruction
*DEEP learning
*INTERPOLATION
*IMAGE reconstruction
Subjects
Details
- Language :
- English
- ISSN :
- 10577149
- Volume :
- 29
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Image Processing
- Publication Type :
- Academic Journal
- Accession number :
- 170078479
- Full Text :
- https://doi.org/10.1109/TIP.2020.2999853