Single Image Focus Editing

Abstract

In this paper, we present a postprocessing approach to tackle the single image focus editing problem. In detail, the proposed method can accomplish the tasks of focus map estimation, image refocusing and defocusing. Given an image with a mixture of focused and defocused objects, we first detect the edges and then estimate the focus map based on the edge blurriness which is depicted explicitly with a well-parameterized model. The image refocusing problem is addressed in an elaborate blind deconvolution framework, where the image prior is modeled well by using both global and local constraints. Especially, we correct the defocused blurry edges to sharp ones with the aid of the parametric edge model and then render this cue as a novel local prior to ensure the sharpness of the refocused image. Experimental results demonstrate that the proposed approach performs well in producing different styles of realistic images from a single input by focus editing.