20160511-14 潘金山:Blind Image Deblurring Using Dark Channel Prior

报告嘉宾1：潘金山（大连理工大学）

报告时间：2016年5月11日（星期三）晚20:00（北京时间）

报告题目：Blind Image Deblurring Using Dark Channel Prior

主持人：  左旺孟（哈尔滨工业大学）

报告摘要：We present a simple and effective blind image deblurring method based on the dark channel prior. Our work is inspired by the interesting observation that the dark channel of blurred images is less sparse. While most image patches in the clean image contain some dark pixels, these pixels are not dark when averaged with neighboring high-intensity pixels during the blur process. This change in the sparsity of the dark channel is an inherent property of the blur process, which we both prove mathematically and validate using training data. Therefore, enforcing the sparsity of the dark channel helps blind deblurring on various scenarios, including natural, face, text, and low-illumination images. However, sparsity of the dark channel introduces a non-convex non-linear optimization problem. We introduce a linear approximation of the min operator to compute the dark channel. Our look-up-table-based method converges fast in practice and can be directly extended to non-uniform deblurring. Extensive experiments show that our method achieves state-of-the-art results on deblurring natural images and compares favorably methods that are well-engineered for specific scenarios.

参考文献：

[1] Jinshan Pan, Deqing Sun, Hanspeter Pfister, and Ming-Hsuan Yang, Blind Image Deblurring Using    Dark Channel Prior, CVPR 2016. (Oral).

[2] Jinshan Pan, Zhe Hu, Zhixun Su, and Ming-Hsuan Yang, L0-Regularized Intensity and Gradient Prior for Deblurring Text Images and Beyond, IEEE TPAMI, 2016.

[3] Jinshan Pan, Zhe Hu, Zhixun Su, and Ming-Hsuan Yang, Deblurring Text Images via L0-Regularized Intensity and Gradient Prior, CVPR 2016.

报告人简介：

Jinshan Pan is a Ph.D. student in School of Mathematical Sciences, Dalian University of Technology. He was a joint-training Ph.D. student in Electrical Engineering and Computer Science, University of California at Merced, directed by Prof. Ming-Hsuan Yang from September 2014 to April 2016. He was a visiting Ph.D. student in Visual Computing Group at Harvard University, working with Prof. Hanspeter Pfister and Dr. Deqing Sun in 2015. His research interest includes image deblurring, image/video analysis and enhancement, and related vision problems.

[Slides]