View : 1226 Download: 0
Unified confidence estimation networks for robust stereo matching
- Title
- Unified confidence estimation networks for robust stereo matching
- Authors
- Kim S.; Min D.; Sohn K.
- Ewha Authors
- 민동보
- SCOPUS Author ID
- 민동보
- Issue Date
- 2019
- Journal Title
- IEEE Transactions on Image Processing
- ISSN
- 1057-7149
- Citation
- IEEE Transactions on Image Processing vol. 28, no. 3, pp. 1299 - 1313
- Keywords
- confidence estimation network; confidence learning; matching probability volume; Stereo confidence
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Indexed
- SCIE; SCOPUS
- Document Type
- Article
- Abstract
- We present a deep architecture that estimates a stereo confidence, which is essential for improving the accuracy of stereo matching algorithms. In contrast to existing methods based on deep convolutional neural networks (CNNs) that rely on only one of the matching cost volume or estimated disparity map, our network estimates the stereo confidence by using the two heterogeneous inputs simultaneously. Specifically, the matching probability volume is first computed from the matching cost volume with residual networks and a pooling module in a manner that yields greater robustness. The confidence is then estimated through a unified deep network that combines confidence features extracted both from the matching probability volume and its corresponding disparity. In addition, our method extracts the confidence features of the disparity map by applying multiple convolutional filters with varying sizes to an input disparity map. To learn our networks in a semi-supervised manner, we propose a novel loss function that use confident points to compute the image reconstruction loss. To validate the effectiveness of our method in a disparity post-processing step, we employ three post-processing approaches; cost modulation, ground control points-based propagation, and aggregated ground control points-based propagation. Experimental results demonstrate that our method outperforms state-of-the-art confidence estimation methods on various benchmarks. © 1992-2012 IEEE.
- DOI
- 10.1109/TIP.2018.2878325
- Appears in Collections:
- 인공지능대학 > 컴퓨터공학과 > Journal papers
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML