Learning a Discriminative Prior for Blind Image Deblurring
It addresses the problem of restoring sharp images from blurred ones for applications in photography and vision, but is incremental as it builds on existing MAP frameworks with a learned prior.
The paper tackles blind image deblurring by learning a discriminative prior using a deep CNN classifier to distinguish clear from blurred images, and results show it performs favorably against state-of-the-art methods across various image types.
We present an effective blind image deblurring method based on a data-driven discriminative prior.Our work is motivated by the fact that a good image prior should favor clear images over blurred images.In this work, we formulate the image prior as a binary classifier which can be achieved by a deep convolutional neural network (CNN).The learned prior is able to distinguish whether an input image is clear or not.Embedded into the maximum a posterior (MAP) framework, it helps blind deblurring in various scenarios, including natural, face, text, and low-illumination images.However, it is difficult to optimize the deblurring method with the learned image prior as it involves a non-linear CNN.Therefore, we develop an efficient numerical approach based on the half-quadratic splitting method and gradient decent algorithm to solve the proposed model.Furthermore, the proposed model can be easily extended to non-uniform deblurring.Both qualitative and quantitative experimental results show that our method performs favorably against state-of-the-art algorithms as well as domain-specific image deblurring approaches.