Single Image Motion Deblurring Using Transparency

One of the key problems of restoring a degraded image from motion blur is the estimation of the unknown shiftinvariant linear blur filter. Several algorithms have been proposed utilizing image intensity or gradient information. In this paper, we separate the image deblurring into filter estimation and image deconvolution processes, and propose a novel algorithm to estimate the motion blur filter from a perspective of alpha values. The relationship between the object boundary transparency and the image motion blur is investigated. We formulate the filter estimation as solving a Maximum a Posteriori (MAP) problem with the defined likelihood and prior on transparency. Our unified approach can be applied to handling both the camera motion blur and the object motion blur.

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Jiaya Jia
• Keywords: Camera Motion Blur, Computer Vision, CVPR 2007, Image Motion Blur, Linear Blur Filter, Motion Blur Filter, Object Motion Blur