# Learning Discriminative Shrinkage Deep Networks for Image Deconvolution

arXiv: https://arxiv.org/abs/2111.13876 · HTML: https://mlsanity.com/paper/2111.13876/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 75 references that are in the map.
- First posted on arXiv 27 Nov 2021.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [Learning Deep CNN Denoiser Prior for Image Restoration](https://mlsanity.com/paper/1704.03264/) (2017)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Deep Unfolding Network for Image Super-Resolution](https://mlsanity.com/paper/2003.10428/) (2020)
- [Maxout Networks](https://mlsanity.com/paper/1302.4389/) (2013)
- [Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal](https://mlsanity.com/paper/1503.00593/) (2015)
- [Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring](https://mlsanity.com/paper/2004.05343/) (2020)
- [Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels](https://mlsanity.com/paper/1903.12529/) (2019)
- [FISTA-Net: Learning A Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging](https://mlsanity.com/paper/2008.02683/) (2020)
- [A Neural Approach to Blind Motion Deblurring](https://mlsanity.com/paper/1603.04771/) (2016)
- [DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring](https://mlsanity.com/paper/2103.09962/) (2021)
- [Deep Mean-Shift Priors for Image Restoration](https://mlsanity.com/paper/1709.03749/) (2017)
- [Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution](https://mlsanity.com/paper/1611.06495/) (2016)
- [Learning Deep Gradient Descent Optimization for Image Deconvolution](https://mlsanity.com/paper/1804.03368/) (2018)
- [End-to-end Interpretable Learning of Non-blind Image Deblurring](https://mlsanity.com/paper/2007.01769/) (2020)
- [Simultaneous Fidelity and Regularization Learning for Image Restoration](https://mlsanity.com/paper/1804.04522/) (2018)
- [Cascades of Regression Tree Fields for Image Restoration](https://mlsanity.com/paper/1404.2086/) (2014)
- [The error accumulation in the conjugate gradient method for degenerate problem](https://mlsanity.com/paper/2004.03231/) (2020)

## Built on by (most cited first, 1 of 1)

- [Denoising Diffusion Models for Plug-and-Play Image Restoration](https://mlsanity.com/paper/2305.08995/) (2023)

## Abstract (arXiv)

Most existing methods usually formulate the non-blind deconvolution problem into a maximum-a-posteriori framework and address it by manually designing kinds of regularization terms and data terms of the latent clear images. However, explicitly designing these two terms is quite challenging and usually leads to complex optimization problems which are difficult to solve. In this paper, we propose an effective non-blind deconvolution approach by learning discriminative shrinkage functions to implicitly model these terms. In contrast to most existing methods that use deep convolutional neural networks (CNNs) or radial basis functions to simply learn the regularization term, we formulate both the data term and regularization term and split the deconvolution model into data-related and regularization-related sub-problems according to the alternating direction method of multipliers. We explore the properties of the Maxout function and develop a deep CNN model with a Maxout layer to learn discriminative shrinkage functions to directly approximate the solutions of these two sub-problems. Moreover, given the fast-Fourier-transform-based image restoration usually leads to ringing artifacts while conjugate-gradient-based approach is time-consuming, we develop the Conjugate Gradient Network to restore the latent clear images effectively and efficiently. Experimental results show that the proposed method performs favorably against the state-of-the-art ones in terms of efficiency and accuracy.