# Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution

arXiv: https://arxiv.org/abs/1611.06495 · HTML: https://mlsanity.com/paper/1611.06495/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2016.

## Built on by (most cited first, 26 of 26)

- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring](https://mlsanity.com/paper/2103.09962/) (2021)
- [Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network](https://mlsanity.com/paper/2104.09556/) (2021)
- [Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image](https://mlsanity.com/paper/2110.05655/) (2021)
- [Gaussian Kernel Mixture Network for Single Image Defocus Deblurring](https://mlsanity.com/paper/2111.00454/) (2021)
- [Universal and Flexible Optical Aberration Correction Using Deep-Prior Based Deconvolution](https://mlsanity.com/paper/2104.03078/) (2021)
- [Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior](https://mlsanity.com/paper/2210.05361/) (2022)
- [RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining](https://mlsanity.com/paper/2107.06808/) (2021)
- [Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment](https://mlsanity.com/paper/2202.05972/) (2022)
- [INFWIDE: Image and Feature Space Wiener Deconvolution Network for Non-blind Image Deblurring in Low-Light Conditions](https://mlsanity.com/paper/2207.08201/) (2022)
- [CurvPnP: Plug-and-play Blind Image Restoration with Deep Curvature Denoiser](https://mlsanity.com/paper/2211.07286/) (2022)
- [Learning Lens Blur Fields](https://mlsanity.com/paper/2310.11535/) (2023)
- [Real-Time Under-Display Cameras Image Restoration and HDR on Mobile Devices](https://mlsanity.com/paper/2211.14040/) (2022)
- [Deep Richardson-Lucy Deconvolution for Low-Light Image Deblurring](https://mlsanity.com/paper/2308.05543/) (2023)
- [Deep Idempotent Network for Efficient Single Image Blind Deblurring](https://mlsanity.com/paper/2210.07122/) (2022)
- [Learning to See Through Dazzle](https://mlsanity.com/paper/2402.15919/) (2024)
- [Semi- and Self-Supervised Multi-View Fusion of 3D Microscopy Images using Generative Adversarial Networks](https://mlsanity.com/paper/2108.02743/) (2021)
- [A Simple And Effective Filtering Scheme For Improving Neural Fields](https://mlsanity.com/paper/2201.13013/) (2022)
- [Robust Scene Inference under Noise-Blur Dual Corruptions](https://mlsanity.com/paper/2207.11643/) (2022)
- [Reverse Convolution and Its Applications to Image Restoration](https://mlsanity.com/paper/2508.09824/) (2025)
- [Learning Discriminative Shrinkage Deep Networks for Image Deconvolution](https://mlsanity.com/paper/2111.13876/) (2021)
- [NBD-GAP: Non-Blind Image Deblurring Without Clean Target Images](https://mlsanity.com/paper/2209.09498/) (2022)
- [Leveraging Classic Deconvolution and Feature Extraction in Zero-Shot Image Restoration](https://mlsanity.com/paper/2310.02097/) (2023)
- [Single-image Defocus Deblurring by Integration of Defocus Map Prediction Tracing the Inverse Problem Computation](https://mlsanity.com/paper/2207.03047/) (2022)
- [DELAD: Deep Landweber-guided deconvolution with Hessian and sparse prior](https://mlsanity.com/paper/2209.15377/) (2022)
- [ErA: Error-Aware Deep Unrolling Network for Single Image Defocus Deblurring](https://mlsanity.com/paper/2606.06540/) (2026)

## Abstract (arXiv)

In this paper, we propose a fully convolutional networks for iterative non-blind deconvolution We decompose the non-blind deconvolution problem into image denoising and image deconvolution. We train a FCNN to remove noises in the gradient domain and use the learned gradients to guide the image deconvolution step. In contrast to the existing deep neural network based methods, we iteratively deconvolve the blurred images in a multi-stage framework. The proposed method is able to learn an adaptive image prior, which keeps both local (details) and global (structures) information. Both quantitative and qualitative evaluations on benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art algorithms in terms of quality and speed.