Unnatural L0 Sparse Representation for Natural Image Deblurring

Li Xu    Shicheng Zheng     Jiaya Jia

Blurred Image Blur Removed Image

Abstract

We show that the success of previous maximum a posterior (MAP) based blur removal methods partly stems from their respective intermediate steps, which implicitly or explicitly create an unnatural representation containing salient image structures. We propose a generalized and mathematically sound L0 sparse expression, together with a new effective method, for motion deblurring. Our system does not require extra filtering during optimization and demonstrates fast energy decreasing, making a small number of iterations enough for convergence. It also provides a unified framework for both uniform and non-uniform motion deblurring. We extensively validate our method and show comparison with other approaches with respect to convergence speed, running time, and result quality.


Downloads

Snapshot for paper "Unnatural L0 Sparse Representation for Natural Image Deblurring"
Li Xu, Shicheng Zheng, Jiaya Jia
IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2013

   Paper (pdf, 3MB)

   Supplementary File (pdf, 60KB)

   Deblurring Software 

   Non-unifrom Deblurring Executable (Matlab .p executable) 

 


Our Deblurring Work

L0 Sparsity Motion Deblurring

Depth-Aware Motion Deblurring

Large-Kernel Robust Motion Deblurring

High-Quality Iterative Optimization

  Rotational Motion Deblurring

  Transparency-based Deblurring

 

 

Other Related Projects

L0 Gradient Minimization

Relative Total Variation

Contrast Preserving Decolorization

 


Examples

Blind Deconvolution Benchmark

Blurred Image Fergus et al. Siggraph 06 Shan et al. Siggraph 08 Cho and Lee Siggraph Asia 09
Xu and Jia ECCV 10 Hirsch et al. ICCV 11 Krishnan et al. CVPR 11 Ours
Blurred Image Fergus et al. Siggraph 06 Shan et al. Siggraph 08 Cho and Lee Siggraph Asia 09
Xu and Jia ECCV 10 Whyte et al. CVPR 10 Krishnan et al. CVPR 11 Ours

 

 

Uniform Deblurring

Cho and Lee Siggraph Asia 09 Xu and Jia ECCV 10 Levin et al. CVPR 11 Ours

 

 

Non-Uniform Deblurring

Blurred Image Gupta et al. ECCV 10 Hirsch et al. ICCV 11 Ours
Blurred Image Harmeling et al. NIPS 10 Hirsch et al. ICCV 11 Ours
Blurred Image Gupta et al. ECCV 10 Hirsch et al. ICCV 11 Ours
Blurred Image Cho & Lee Siggraphp Asia 09 Hirsch et al. ICCV 11 Ours
Blurred Image Harmeling et al. NIPS 10 Hirsch et al. ICCV 11 Ours
Blurred Image Whyte et al. CVPR 10 Hirsch et al. ICCV 11 Ours


References

[1] R. Fergus, B. Singh, A. Hertzmann, S.T. Roweis and W.T. Freeman. “Removing camera shake from a single photograph”, SIGGRAPH 2006.

[2] Q. Shan, J. Jia and A. Agarwala. “High-quality motion deblurring from a single image”, SIGGRAPH 2008.

[3] S. Cho and S. Lee. “Fast motion deblurring”, SIGGRAPH ASIA 2009.

[4] L. Xu and J. Jia. “Two-Phase Kernel Estimation for Robust Motion Deblurring”, ECCV 2010.

[5] O. Whyte, J. Sivic, A. Zisserman and J. Ponce. “Non-uniform Deblurring for Shaken Images”, CVPR 2010.

[6] A. Gupta, N. Joshi, L. Zitnick, M. Cohen and B. Curless. “Single Image Deblurring Using Motion Density Functions”, ECCV 2010.

[7] S. Harmeling, M. Hirsch and B. Schölkopf. “Space-Variant Single-Image Blind Deconvolution for Removing Camera Shake”, NIPS 2010.

[8] A. Levin, Y. Weiss, F. Durand, W. T. Freeman. "Efficient Marginal Likelihood Optimization in Blind Deconvolution", CVPR 2011.

[9] D. Krishnan, T. Tay and R. Fergus. “Blind Deconvolution using a Normalized Sparsity Measure”, CVPR 2011.

[10] M. Hirsch, C. Schuler, S. Harmeling and B. Schölkopf. “Fast Removal of Non-uniform Camera Shake”, ICCV 2011.

[11] R. Köhler, M. Hirsch, B. Mohler and B. Schölkopf. “Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database”, ECCV 2012.