Joint Matting and Gradient-Domain Deringing for Image Deblurring

In this paper, we propose a method for removing motion blur and deringing from images, which can be applied to handle both the camera motion blur and the object motion blur. Fully taking the advantage of abundant information of blurred/noisy image pair, we can extract the alpha mattes of same objects in both burred image and noisy image, and then estimate the blur kernel of blurred image using the mattes. In addition, gradient domain smoothness is joined to deconvolution stage to inhibit the ringing artifacts. The experiments demonstrate that, method proposed in this paper is effective and can achieve fair restoration effect.