# Gaussian Kernel Mixture Network for Single Image Defocus Deblurring

arXiv: https://arxiv.org/abs/2111.00454 · HTML: https://mlsanity.com/paper/2111.00454/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 49 references that are in the map.
- First posted on arXiv 31 Oct 2021.

## Builds on (most cited first, 21 of 21)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Deep Stacked Hierarchical Multi-patch Network for Image Deblurring](https://mlsanity.com/paper/1904.03468/) (2019)
- [Deblurring by Realistic Blurring](https://mlsanity.com/paper/2004.01860/) (2020)
- [Defocus Deblurring Using Dual-Pixel Data](https://mlsanity.com/paper/2005.00305/) (2020)
- [Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring](https://mlsanity.com/paper/2004.05343/) (2020)
- [Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training](https://mlsanity.com/paper/1911.07410/) (2019)
- [Iterative Filter Adaptive Network for Single Image Defocus Deblurring](https://mlsanity.com/paper/2108.13610/) (2021)
- [Denoising Prior Driven Deep Neural Network for Image Restoration](https://mlsanity.com/paper/1801.06756/) (2018)
- [Rotate to Attend: Convolutional Triplet Attention Module](https://mlsanity.com/paper/2010.03045/) (2020)
- [Learning to Deblur](https://mlsanity.com/paper/1406.7444/) (2014)
- [Squeeze-and-Attention Networks for Semantic Segmentation](https://mlsanity.com/paper/1909.03402/) (2019)
- [Learning Single Camera Depth Estimation using Dual-Pixels](https://mlsanity.com/paper/1904.05822/) (2019)
- [Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration](https://mlsanity.com/paper/2012.00301/) (2020)
- [Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution](https://mlsanity.com/paper/1611.06495/) (2016)
- [A Unified Approach of Multi-scale Deep and Hand-crafted Features for Defocus Estimation](https://mlsanity.com/paper/1704.08992/) (2017)
- [Learning Deep Gradient Descent Optimization for Image Deconvolution](https://mlsanity.com/paper/1804.03368/) (2018)
- [An Algorithm Unrolling Approach to Deep Image Deblurring](https://mlsanity.com/paper/1902.05399/) (2019)
- [Convergence Analysis of MAP based Blur Kernel Estimation](https://mlsanity.com/paper/1611.07752/) (2016)

## Built on by (most cited first, 20 of 20)

- [Multi-scale frequency separation network for image deblurring](https://mlsanity.com/paper/2206.00798/) (2022)
- [A Unified Framework for Microscopy Defocus Deblur with Multi-Pyramid Transformer and Contrastive Learning](https://mlsanity.com/paper/2403.02611/) (2024)
- [Revisiting Image Deblurring with an Efficient ConvNet](https://mlsanity.com/paper/2302.02234/) (2023)
- [Panchromatic and Multispectral Image Fusion via Alternating Reverse Filtering Network](https://mlsanity.com/paper/2210.08181/) (2022)
- [A Progressive Image Restoration Network for High-order Degradation Imaging in Remote Sensing](https://mlsanity.com/paper/2412.07195/) (2024)
- [Plug-and-Play Image Restoration with Flow Matching: A Continuous Viewpoint](https://mlsanity.com/paper/2512.04283/) (2025)
- [A Multi-scale Generalized Shrinkage Threshold Network for Image Blind Deblurring in Remote Sensing](https://mlsanity.com/paper/2309.07524/) (2023)
- [A Comprehensive Survey on Deep Neural Image Deblurring](https://mlsanity.com/paper/2310.04719/) (2023)
- [Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks](https://mlsanity.com/paper/2501.09052/) (2025)
- [Frequency-Driven Inverse Kernel Prediction for Single Image Defocus Deblurring](https://mlsanity.com/paper/2508.12736/) (2025)
- [Defocus Blur Synthesis and Deblurring via Interpolation and Extrapolation in Latent Space](https://mlsanity.com/paper/2307.15461/) (2023)
- [SR-R2KAC: Improving Single Image Defocus Deblurring](https://mlsanity.com/paper/2307.16242/) (2023)
- [Pathology Image Restoration via Mixture of Prompts](https://mlsanity.com/paper/2503.12399/) (2025)
- [Image Restoration via Multi-domain Learning](https://mlsanity.com/paper/2505.05504/) (2025)
- [Joint Deblurring and 3D Reconstruction for Macrophotography](https://mlsanity.com/paper/2510.01640/) (2025)
- [Generative Multi-Focus Image Fusion](https://mlsanity.com/paper/2512.21495/) (2025)
- [Discontinuous Galerkin Neural Operator for Pathology Defocus Deblurring](https://mlsanity.com/paper/2605.23282/) (2026)
- [ErA: Error-Aware Deep Unrolling Network for Single Image Defocus Deblurring](https://mlsanity.com/paper/2606.06540/) (2026)
- [Leveraging Phase Information to Boost Unrolled Network Learning for Image Deblurring](https://mlsanity.com/paper/2607.00251/) (2026)
- [The RealDefocus Benchmark for Defocus Deblurring](https://mlsanity.com/paper/2607.21078/) (2026)

## Abstract (arXiv)

Defocus blur is one kind of blur effects often seen in images, which is challenging to remove due to its spatially variant amount. This paper presents an end-to-end deep learning approach for removing defocus blur from a single image, so as to have an all-in-focus image for consequent vision tasks. First, a pixel-wise Gaussian kernel mixture (GKM) model is proposed for representing spatially variant defocus blur kernels in an efficient linear parametric form, with higher accuracy than existing models. Then, a deep neural network called GKMNet is developed by unrolling a fixed-point iteration of the GKM-based deblurring. The GKMNet is built on a lightweight scale-recurrent architecture, with a scale-recurrent attention module for estimating the mixing coefficients in GKM for defocus deblurring. Extensive experiments show that the GKMNet not only noticeably outperforms existing defocus deblurring methods, but also has its advantages in terms of model complexity and computational efficiency.