Depth-Aware and Spatially-Varying (Non-uniform) Motion Deblurring

Li Xu              Jiaya Jia

Left Image Right Image Disparity Map Blur Removed Image

Abstract

Motion blur removal from images sometimes need to estimate spatially-varying point spread functions (PSFs). We address two critical problems in this process. 

Our framework applies to general single-image and stereo-image spatially-varying deblurring. 


Downloads

Snapshot for paper "Depth-Aware Motion Deblurring"
Li Xu and Jiaya Jia
IEEE International Conference on Computational Photography (ICCP), 2012


   [Paper (pdf, 4.6MB)]

  [Presentation Slides]

 


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

  


More Examples

Stereopsis Deblurring

Left Image Right Image Blur Removed Image (Left) Blur Removed Image (Right)
Left Image Right Image Blur Removed Image (Left) Xu and Jia ECCV 10

 

Spatially-Varying Deblurring

Input Image Whyte et al. CVPR 10 Our Result Our PSFs
Input Image Joshi et al. Siggraph 10 Our Result Our PSFs
Input Image Joshi et al. Siggraph 10 Our Result Our PSFs
Input Image Gupta et al. ECCV 10 Our Result Our PSFs


References

[1] L. Xu, J. Jia, Two-phase Kernel Estimation for Robust Motion Deblurring, ECCV 2010

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

[2] N. Joshi, S.B. Kang, L. Zitnick, and R. Szeliski, Image Deblurring with Inertial Measurement Sensors. ACM SIGGRAPH 2010

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