# Learning a Discriminative Prior for Blind Image Deblurring Source: [Learning a Discriminative Prior for Blind Image Deblurring]() Collection index: [llms.txt]() Data updated: 2025-12-25T04:23:46.573Z Authors: Lerenhan Li, Jinshan Pan, Wei-Sheng Lai, Changxin Gao, Nong Sang, Ming-Hsuan Yang Published: 2018-03-09T02:48:10.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Deblurring on text image dataset 15 clear images, 8 blur kernels](): Image Deblurring; text image dataset 15 clear images, 8 blur kernels; Avg PSNR: 28.1. - [Blind Image Deblurring on Generic images 255 x 255 (Runtime)](): Blind Image Deblurring; Generic images 255 x 255; Average Runtime (s): 109.27. - [Blind Image Deblurring on Generic images 600 x 600 (runtime)](): Blind Image Deblurring; Generic images 600 x 600; Average Runtime (s): 379.52. - [Blind Image Deblurring on Generic images 800 x 800 (Runtime)](): Blind Image Deblurring; Generic images 800 x 800; Average Runtime (s): 654.65. ## Original sources and implementation [Original paper]() [PDF]()