[cs-talks] IVC Seminar, Deqing Sun, Monday March 27, 1pm @ CAS 326
Harrington, Jacob Walter
jwharrin at bu.edu
Thu Mar 23 12:11:28 EDT 2017
Blind Image Deblurring Using Dark Channel Prior
Deqing Sun, Senior Research Scientist, NVIDIA Research
Monday March 27th, 1pm – 2pm in 725 Commonwealth Ave, Room 326
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 nonlinear 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. In addition, we show that the proposed prior can be applied to image dehazing.
Deqing Sun is a Senior Research Scientist at NVIDIA Research. Before that, he was a postdoctoral research fellow (and is a visiting researcher) in Prof. Hanspeter Pfister’s visual computing group at Harvard University. He received his BEng degree in Electronic and Information Engineering from Harbin Institute of Technology, his MPhil degree in Electronic Engineering from the Chinese University of Hong Kong, and his PhD degrees in Computer Science from Brown University working with Prof. Michael J. Black. He was a research intern at Microsoft Research New England from Oct. to Dec. 2010 working with Dr. Ce Liu. His research interests include computer vision, machine learning, and computational photography, particularly motion estimation and segmentation and the applications to computational video.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the cs-talks