Abstract
Motion blur due to camera shake is one of the predominant sources of degradation in handheld photography. Single image blind de- convolution (BD) or motion deblurring aims at restoring a sharp latent image from the blurred recorded picture without knowing the camera mo- tion that took place during the exposure. BD is a long-standing problem, but has attracted much attention recently, cumulating in several algo- rithms able to restore photos degraded by real camera motion in high quality. In this paper, we present a benchmark dataset for motion deblur- ring that allows quantitative performance evaluation and comparison of recent approaches featuring non-uniform blur models. To this end, we record and analyse real camera motion, which is played back on a robot platform such that we can record a sequence of sharp images sampling the six dimensional camera motion tra jectory. The goal of deblurring is to recover one of these sharp images, and our dataset contains all infor- mation to assess how closely various algorithms approximate that goal. In a comprehensive comparison, we evaluate state-of-the-art single image BD algorithms incorporating uniform and non-uniform blur models.