Blur Kernel Estimation Using Normalized Color-line Priors




Abstract
This paper proposes a single-image blur kernel estimation algorithm that utilizes the normalized color-line prior to restore sharp edges without altering edge structures or enhancing noise. The proposed prior is derived from the color-line model, which has been successfully applied to non-blind deconvolution and many computer vision problems. In this paper, we show that the original color-line prior is not effective for blur kernel estimation and propose a normalized color-line prior which can better enhance edge contrasts. By optimizing the proposed prior, our method gradually enhances the sharpness of the intermediate patches without using heuristic filters or external patch priors. The intermediate patches can then guide the estimation of the blur kernel. A comprehensive evaluation on a large image deblurring dataset shows that our algorithm achieves the state-of-the-art results.


Paper


CVPR 2015 paper (10 MB)


Citation
Wei-Sheng Lai, Jian-Jiun Ding, Yen-Yu Lin, and Yung-Yu Chuang. "Blur Kernel Estimation Using Normalized Color-line Priors." In Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR 2015), June 2015.

Bibtex
@INPROCEEDINGS{colorline_deblur_cvpr2015,
    AUTHOR    = {Wei-Sheng Lai, Jian-Jiun Ding, Yen-Yu Lin, and Yung-Yu Chuang}, 
    TITLE     = {Blur Kernel Estimation Using Normalized Color-line Priors}, 
    YEAR      = {2015},
    MONTH     = {June},
    BOOKTITLE = {Proceedings of IEEE Conferene on Computer Vision and Pattern Recognition (CVPR 2015)},
    PAGES     = {to appear}
}

Deblurred Results
Blurry Image
Cho and Lee
Xu and Jia
Krishnan et al.
Levin et al.
Sun et al.
Michaeli and Irani
Ours

Blurry Image
Cho and Lee
Xu and Jia
Krishnan et al.
Levin et al.
Sun et al.
Michaeli and Irani
Ours

Blurry Image
Cho and Lee
Xu and Jia
Krishnan et al.
Levin et al.
Sun et al.
Michaeli and Irani
Ours

Blurry Image
Cho and Lee
Xu and Jia
Krishnan et al.
Levin et al.
Sun et al.
Michaeli and Irani
Ours

Blurry Image
Cho and Lee
Xu and Jia
Krishnan et al.
Levin et al.
Sun et al.
Michaeli and Irani
Ours


Reference
  • S. Cho and S. Lee. “Fast motion deblurring”, SIGGRAPH Asia 2009.
  • L. Xu and J. Jia. “Two-Phase Kernel Estimation for Robust Motion Deblurring”, ECCV 2010.
  • D. Krishnan, T. Tay and R. Fergus. “Blind Deconvolution using a Normalized Sparsity Measure”, CVPR 2011.
  • A. Levin, Y. Weiss, F. Durand, W. T. Freeman. "Efficient Marginal Likelihood Optimization in Blind Deconvolution", CVPR 2011.
  • L. Sun, S. Cho, J. Wang, and J. Hays. "Edge-based Blur Kernel Estimation Using Patch Priors", ICCP 2013.
  • T. Michaeli and M. Irani. "Blind Deblurring Using Internal Patch Recurrence", ECCV 2014.
  • N. Joshi, C. L. Zitnick, R. Szeliski, D. Kriegman. "Image Deblurring and Denoising using Color Priors", CVPR 2009.