Blind motion deblurring using optical flow

In recent years, a lot of motion deblurring methods have been proposed, most of which divide the motion blur problem into two parts: camera shake and object motion, and just deal with only one side of the problem. As a result, in this paper we focus on seeking a effective model to handle these two kinds of motion blur simultaneously. An optical flow based model is then proposed. In particular, the blurred image can be formulated as an integration of some clear intermediate images after optical based transformed. Meanwhile an effective algorithm based on this new model is introduced to deblur different types of blurry images. In this work, we not only use the optical flow to represent the blur process but also derive the optical flow estimation algorithm to help estimate the non-uniform PSF for each pixel. In addition, we show that by incorporating different kinds of constraints our method can get more robust and stable results. The experiments on both synthesized and real images show that our algorithm can effectively recover the latent images and get comparable results with some state of the art algorithms.