Abstract
Camera shake leads to non-uniform image blurs. State-of-the-art methods for removing camera shake model the blur as a linear combination of homographically transformed versions of the true image. While this is conceptually interesting, the resulting algorithms are computationally demanding. In this paper we develop a forward model based on the efficient filter flow framework, incorporating the particularities of camera shake, and show how an efficient algorithm for blur removal can be obtained. Comprehensive comparisons on a number of real-world blurry images show that our approach is not only substantially faster, but it also leads to better deblurring results.

Downloads • Paper (pdf) • Supplementary Material (zipped pdf) • Poster (pdf) • Talk Slides (pdf) • Video of Talk at ICCV 2011 • Example Images • Comparison with Gupta et al., Single Image Deblurring Using Motion Density Functions, ECCV 2010. Blurred image Xu et al., ECCV 2010 Gupta et al., ECCV 2010 Our approach • Comparison with Harmeling et al., Space-Variant Single-Image Blind Deconvolution for Removing Camera Shake, NIPS 2010. Blurred image Cho et al., SIGGRAPH 2009 Harmeling et al., NIPS 2010 Our approach • Comparison with Joshi et al., Image deblurring using inertial measurement sensors, Siggraph 2010. Blurred image Xu et al., ECCV 2010 Joshi et al., Siggraph 2010 Our approach • Comparison with Whyte et al., Non-uniform Deblurring for Shaken Images, CVPR 2010. Blurred image Fergus et al., Siggraph 2006 Whyte et al., CVPR 2010 Our approach