A Deconvolutional Deblurring Algorithm Based on Dual-Channel Images
Source abstract
Abstract
Aiming at the motion blur restoration of large-scale dual-channel space-variant images, this paper proposes a dual-channel image deblurring method based on the idea of block aggregation, by studying imaging principles and existing algorithms. The study first analyzed the model of dual-channel space-variant imaging, reconstructed the kernel estimation process using the side prior information from the correlation of the two-channel images, and then used a clustering algorithm to classify kernels and restore the images. In the kernel estimation process, the study proposed two kinds of regularization terms. One is based on image correlation, and the other is based on the information from another channel input. In the image restoration process, the mean-shift clustering algorithm was used to calculate the block image kernel weights and reconstruct the final restored image according to the weights. As the experimental section shows, the restoration effect of this algorithm was better than that of the other compared algorithms.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image Processing Techniques · Image and Signal Denoising Methods · Image Processing Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Aerospace Information Research Institute, Chinese Academy of Sciences, No. 9 Dengzhuang South Road, Haidian District, Beijing 100094, China
School of Optoelectronics, University of Chinese of Academy Sciences, No. 19 (A) Yuquan Road, Shijingshan District, Beijing 100039, China
Department of Key Laboratory of Computational Optical Imaging Technology, Chinese Academy of Sciences, No. 9 Dengzhuang South Road, Haidian District, Beijing 100094, China
School of Instrumentation and Optoelectronic Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100049, China
Funding
National Natural Science Foundation of China · National Defense Science and technology innovation fund of the Chinese Academy of Sciences · Science Technology Foundation Strengthening Field Fund Project
References (25)
Show source-provided references
1. Removing camera shake from a single photograph
2. Image and Depth from a Conventional Camera with a Coded Aperture
3. Variational Dirichlet Blur Kernel Estimation10.1109/TIP.2015.2478407 ↗
4. Synthesis of high dynamic range motion blur free image from multiple captures10.1109/TCSI.2003.809815 ↗
5. Li, Z., Deshpande, A., and Xin, C. (2010, January 13–18). Denoising vs. deblurring: HDR imaging techniques using moving cameras. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.
6. Two motion-blurred images are better than one10.1016/j.patrec.2004.10.017 ↗
7. Yuan, L., Sun, J., Quan, L., and Shum, H.Y. (2007). Image deblurring with blurred noisy image pairs. ACM SIGGRAPH 2007 Papers, Proceedings of the SIGGRAPH07: Special Interest Group on Computer Graphics and Interactive Techniques Conference, San Diego, CA, USA, 5–9 August 2007, Association for Computing Machinery.10.1145/1275808.1276379 ↗
8. A general framework for frequency domain multi-channel signal processing10.1109/83.236528 ↗
9. Multichannel blind deconvolution of spatially misaligned images10.1109/TIP.2005.849322 ↗
10. Sroubek, F., Flusser, J., and Cristobal, G. (2007). Multiframe Blind Deconvolution Coupled with Frame Registration and Resolution Enhancement, CRC Press.
11. Robust Multichannel Blind Deconvolution via Fast Alternating Minimization10.1109/TIP.2011.2175740 ↗
12. BM3D filter in salt-and-pepper noise removal10.1186/s13640-016-0113-x ↗
13. Space-variant blur kernel estimation and image deblurring through kernel clustering10.1016/j.image.2019.04.014 ↗
14. Xu, Z., Fugen, Z., and Bei, X.Z. (2013, January 15–18). Blind deconvolution using a nondimensional Gaussianity measure. Proceedings of the 2014 IEEE International Conference on Image Processing, Melbourne, VIC, Australia.
15. Perfect Blind Restoration of Images Blurred by Multiple Filters: Theory and Efficient Algorithms10.1109/83.743855 ↗
16. Application of energy functional regularization model in image restoration
17. Yang, L., and Ji, H. (2019, January 15–20). A Variational EM Framework With Adaptive Edge Selection for Blind Motion Deblurring. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.01041 ↗
18. An iterative regularization method for total variation-based image restoration10.1137/040605412 ↗
19. A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems10.1137/080716542 ↗
20. Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers10.1561/2200000016 ↗
21. A Simple Local Minimal Intensity Prior and An Improved Algorithm for Blind Image Deblurring10.1109/TCSVT.2020.3034137 ↗
22. Graph-Based Blind Image Deblurring From a Single Photograph10.1109/TIP.2018.2874290 ↗
23. Pan, L., Hartley, R., Liu, M., and Dai, Y. (2019, January 15–20). Phase-Only Image Based Kernel Estimation for Single Image Blind Deblurring. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00619 ↗
24. (2017). 2017 Photography Electronic Still Picture Imaging Resolution and Spatial Frequency Responses (Standard No. ISO 122333).
25. Making a “Completely Blind” Image Quality Analyzer10.1109/LSP.2012.2227726 ↗