Forward Motion Deblurring

Shicheng Zheng    Li Xu     Jiaya Jia

Forward Motion Blurred Image Blur Removed Image

Abstract

We handle a special type of motion blur considering that cameras move primarily forward or backward. Solving this type of blur is of unique practical importance since nearly all car, traffic and bike-mounted cameras follow out-ofplane translational motion. We start with the study of geometric models and analyze the difficulty of existing methods to deal with them. We also propose a solution accounting for depth variation. Homographies associated with different 3D planes are considered and solved for in an optimization framework. Our method is verified on several natural image examples that cannot be satisfyingly dealt with by previous methods.


Downloads

Snapshot for paper "Forward Motion Deblurring"
Shicheng Zheng, Li Xu and Jiaya Jia
IEEE International Conference on Computer Vision (ICCV), 2013


   [Paper (pdf, 950kb)]
   [Image Data] (Coming Soon)

 


Our Other Deblurring Work

  Transparency-based Deblurring

  Rotational Motion Deblurring

High-Quality Iterative Optimization

Large-Kernel Robust Motion Deblurring

Depth-Aware Motion Deblurring

L0 Sparsity Motion Deblurring

  


Examples

Forward Blur Visualization

Dotted pattern Forward blur

 

Deblurring Results

Blurr Image [3] [2] Ours
Blurr Image [1] [4] Ours
Blurr Image [1] [5] Ours


References

[1] S. Cho and S. Lee. Fast motion deblurring. SIGGRAPH ASIA 2009.

[2] L. Xu and J. Jia. Two-Phase Kernel Estimation for Robust Motion Deblurring. ECCV 2010.

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

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

[5] L. Xu, S. Zheng, and J. Jia. Unnatural L0 Sparse Representation for Natural Image Deblurring. CVPR 2013.