Neural Blind Deconvolution Using Deep Priors

By Dongwei Ren, Kai Zhang, Qilong Wang, Qinghua Hu, Wangmeng Zuo. Computer Vision and Pattern Recognition, 2019

332 citations recorded by the source corpus.

Blind deconvolution is a classical yet challenging low-level vision problem with many real-world applications. Traditional maximum a posterior (MAP) based methods rely heavily on fixed and handcrafted priors that certainly are insufficient in characterizing clean images and blur kernels, and usually adopt specially designed alternating minimization to avoid trivial solution. In contrast, existing deep motion deblurring networks learn from massive training images the mapping to clean image or blur kernel, but are limited in handling various complex and large size blur kernels. To connect MAP and deep models, we in this paper present two generative networks for respectively modeling the deep priors of clean image and blur kernel, and propose an unconstrained neural optimization solution to blind deconvolution. In particular, we adopt an asymmetric Autoencoder with skip connections for generating latent clean image, and a fully-connected network (FCN) for generating blur kernel. Moreover, the SoftMax nonlinearity is applied to the output layer of FCN to meet the non-negative and equality constraints. The process of neural optimization can be explained as a kind of ''zero-shot" self-supervised learning of the generative networks, and thus our proposed method is dubbed SelfDeblur. Experimental results show that our SelfDeblur can achieve notable quantitative gains as well as more visually plausible deblurring results in comparison to state-of-the-art blind deconvolution methods on benchmark datasets and real-world blurry images. The source code is publicly available at https://github.com/csdwren/SelfDeblur

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f48974521b27a462c30c3b2b2cbd0aee7b6bab59

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Flow-based Kernel Prior with Application to Blind Super-Resolution (2021, methodology): “The total number of flow blocks and FCN depth are set to 5 and 3, respectively.”
Deep Unfolding Network for Image Super-Resolution (2020, background): “While learning-based blind image restoration has recently received considerable attention [12, 39, 43, 50, 62], we note that this work focuses on non-blind SISR which assumes the LR image, blur kernel and noise level are known beforehand.”
Deep Image Deblurring: A Survey (2022, methodology): “Deconvolution with Denoising Representative algorithms in this category include (Ren et al. 2018; Schuler et al. 2013; Xu et al. 2014; Zhang et al. 2017, ?). Schuler et al. (2013) develop a multi-layer perceptron (MLP) to deconvolve images. This approach first recovers a sharp image through a regula”