Learning to Estimate and Remove Non-uniform Image Blur

Florent Couzinie-Devy (1, 2) , Jian Sun (1, 2, 3) , Karteek Alahari (1, 2) , Jean Ponce (1, 2)

1 WILLOW - Models of visual object recognition and scene understanding
2 LIENS - Laboratoire d'informatique de l'école normale supérieure
3 Xjtu - Xi'an Jiaotong University

This paper addresses the problem of restoring images subjected to unknown and spatially varying blur caused by defocus or linear (say, horizontal) motion. The estimation of the global (non-uniform) image blur is cast as a multi-label energy minimization problem. The energy is the sum of unary terms corresponding to learned local blur estimators, and binary ones corresponding to blur smoothness. Its global minimum is found using Ishikawa's method by exploiting the natural order of discretized blur values for linear motions and defocus. Once the blur has been estimated, the image is restored using a robust (non-uniform) deblurring algorithm based on sparse regularization with global image statistics. The proposed algorithm outputs both a segmentation of the image into uniform-blur layers and an estimate of the corresponding sharp image. We present qualitative results on real images, and use synthetic data to quantitatively compare our approach to the publicly available implementation of Chakrabarti et al. (2010).

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Florent Couzinie-Devy, Jian Sun, Karteek Alahari, Jean Ponce. Learning to Estimate and Remove Non-uniform Image Blur. CVPR - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2013, Portland, United States. pp.1075-1082, ⟨10.1109/CVPR.2013.143⟩. ⟨hal-00818175⟩