High-quality Motion Deblurring from a Single Image

Qi Shan           Jiaya Jia          Aseem Agarwala

Abstract

We present a new algorithm for removing motion blur from a single image. Our method computes a deblurred image using a unified probabilistic model of both blur kernel estimation and unblurred image restoration. We present an analysis of the causes of common artifacts found in current deblurring methods, and then introduce several novel terms within this probabilistic model that are inspired by our analysis. These terms include a model of the spatial randomness of noise in the blurred image, as well a new local smoothness prior that reduces ringing artifacts by constraining contrast in the unblurred image wherever the blurred image exhibits low contrast. Finally, we describe an efficient optimization scheme that alternates between blur kernel estimation and unblurred image restoration until convergence. As a result of these steps, we are able to produce high quality deblurred results in low computation time. We are even able to produce results of comparable quality to techniques that require additional input images beyond a single blurry photograph, and to methods that require additional hardware.


Downloads

[Paper], [Talk Slides], [Additional Programming Details]

[Image Deblurring Executable], [Image Non-blind Deconvolution Executable]

BibTex:

@article{hqdeblurring_siggraph2008,
    author = {Qi Shan and Jiaya Jia and Aseem Agarwala},
    title = {High-quality Motion Deblurring from a Single Image},
    journal = {ACM Transactions on Graphics (SIGGRAPH)},
    year = {2008}, 
}

 


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

  


 

Input Images

Ω (in the red channel)

Results