This project is about the recovery of blurring images with an unkown blurring kernel, especially the recovery of motion-blurred images. How to recover a clear image from a single motion-blurred image has long been a challenging open problem in digital imaging. A regularization-based approach is proposed to remove motion blurring from the image by regularizing the sparsity of both the original image and the motion-blur kernel under tight wavelet frame systems. An adapted version of the wavelet frame-based model is proposed to efficiently solve the resulting minimization problem using an iterative thresholding algorithm. The experiments on both synthesized images and real images show that our approaches can effectively remove complex motion blurring from natural images without requiring any prior information of the motion-blur kernel.
-
- Jianfeng Cai, Hui Ji, Chaoqiang Liu, Zuowei Shen, Framelet based blind motion deblurring from a single image, IEEE Transactions on Image Processing, 21(2), (2012), 562-572. PDF
- Hui Ji, Jia Li, Zuowei Shen, Kang Wang, Image deconvolution using a characterization of sharp images in wavelet domain, Applied and Computational Harmonic Analysis, 32(2), (2012), 295-304. PDF
- Bin Dong, Hui Ji, Jia Li, Zuowei Shen, Yuhong Xu, Wavelet frame based blind image inpainting, Applied and Computational Harmonic Analysis, 32(2), (2012), 268-279. PDF
- Jianfeng Cai, Hui Ji, Chaoqiang Liu, Zuowei Shen, Blind motion deblurring from a single image using sparse approximation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, 2009. PDF
- Jianfeng Cai, Hui Ji, Chaoqiang Liu, Zuowei Shen, High-quality curvelet-based motion deblurring using an image pair, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, 2009. PDF
- Jianfeng Cai, Hui Ji, Chaoqiang Liu, Zuowei Shen, Blind motion deblurring using multiple images, Journal of Computational Physics, 228 (14), 2009, 5057-5071. PDF