Joint image denoising and disparity estimation via stereo structure PCA and noise-tolerant cost
Publication Type
Journal Article
Publication Date
9-2017
Abstract
Stereo cameras are now commonly available on cars and mobile phones. However, the captured images may suffer from low image quality under noisy conditions, producing inaccurate disparity. In this paper, we aim at jointly restoring a clean image pair and estimating the corresponding disparity. To this end, we propose a new joint framework that iteratively optimizes these two different tasks in a multi-scale fashion. First, structure information between the stereo pair is utilized to denoise the images using a non-local means strategy. Second, a new noise-tolerant cost function is proposed for noisy stereo matching. These two terms are integrated into a multi-scale framework in which cross-scale information is leveraged to further improve both denoising and stereo matching. Extensive experiments on datasets captured from indoor, outdoor, and low-light conditions show that the proposed method achieves superior performance than the state-of-the-art image denoising and disparity estimation methods. While it outperforms multi-image denoising methods by about 2 dB on average, it achieves a 50% error reduction over radiometric-change-robust stereo matching on the challenging KITTI dataset.
Keywords
Stereo matching, Image denoising, Disparity estimation, Non-local means
Discipline
Information Security
Research Areas
Information Systems and Management
Publication
International Journal of Computer Vision
Volume
124
Issue
2
First Page
204
Last Page
222
ISSN
0920-5691
Identifier
10.1007/s11263-017-1015-9
Publisher
Springer
Citation
JIAO, Jianbo; YANG, Qingxiong; HE, Shengfeng; GU, Shuhang; ZHANG, Lei; and LAU, Rynson W. H..
Joint image denoising and disparity estimation via stereo structure PCA and noise-tolerant cost. (2017). International Journal of Computer Vision. 124, (2), 204-222.
Available at: https://ink.library.smu.edu.sg/sis_research/7868
Additional URL
https://doi.org/10.1007/s11263-017-1015-9