# Blind Motion Deblurring with Pixel-Wise Kernel Estimation via Kernel Prediction Networks

arXiv: https://arxiv.org/abs/2308.02947 · HTML: https://mlsanity.com/paper/2308.02947/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 81 references that are in the map.
- First posted on arXiv 5 Aug 2023.

## Builds on (most cited first, 30 of 31)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Rethinking Coarse-to-Fine Approach in Single Image Deblurring](https://mlsanity.com/paper/2108.05054/) (2021)
- [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016)
- [ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data](https://mlsanity.com/paper/1904.00592/) (2019)
- [Video Frame Interpolation via Adaptive Separable Convolution](https://mlsanity.com/paper/1708.01692/) (2017)
- [Deep Stacked Hierarchical Multi-patch Network for Image Deblurring](https://mlsanity.com/paper/1904.03468/) (2019)
- [Video Frame Interpolation via Adaptive Convolution](https://mlsanity.com/paper/1703.07514/) (2017)
- [Burst Denoising with Kernel Prediction Networks](https://mlsanity.com/paper/1712.02327/) (2017)
- [Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal](https://mlsanity.com/paper/1503.00593/) (2015)
- [From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur](https://mlsanity.com/paper/1612.02583/) (2016)
- [Explore Image Deblurring via Blur Kernel Space](https://mlsanity.com/paper/2104.00317/) (2021)
- [Basis Prediction Networks for Effective Burst Denoising with Large Kernels](https://mlsanity.com/paper/1912.04421/) (2019)
- [Reblur2Deblur: Deblurring Videos via Self-Supervised Learning](https://mlsanity.com/paper/1801.05117/) (2018)
- [Super-Resolution with Deep Convolutional Sufficient Statistics](https://mlsanity.com/paper/1511.05666/) (2015)
- [Exposure Trajectory Recovery from Motion Blur](https://mlsanity.com/paper/2010.02484/) (2020)
- [Deblurring using Analysis-Synthesis Networks Pair](https://mlsanity.com/paper/2004.02956/) (2020)
- [Spatially-Varying Blur Detection Based on Multiscale Fused and Sorted Transform Coefficients of Gradient Magnitudes](https://mlsanity.com/paper/1703.07478/) (2017)
- [Removing Camera Shake via Weighted Fourier Burst Accumulation](https://mlsanity.com/paper/1505.02731/) (2015)
- [Linearized ADMM for Non-convex Non-smooth Optimization with Convergence Analysis](https://mlsanity.com/paper/1705.02502/) (2017)
- [Optical Flow Estimation from a Single Motion-blurred Image](https://mlsanity.com/paper/2103.02996/) (2021)
- [Deep Model-Based Super-Resolution with Non-uniform Blur](https://mlsanity.com/paper/2204.10109/) (2022)

## Built on by (most cited first, 8 of 8)

- [Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution](https://mlsanity.com/paper/2309.00287/) (2023)
- [Reconstruct Anything Model: a lightweight general model for computational imaging](https://mlsanity.com/paper/2503.08915/) (2025)
- [Blur2seq: Blind Deblurring and Camera Trajectory Estimation from a Single Camera Motion-blurred Image](https://mlsanity.com/paper/2510.20539/) (2025)
- [Spread Your Wings: A Radial Strip Transformer for Image Deblurring](https://mlsanity.com/paper/2404.00358/) (2024)
- [Frequency-domain Learning with Kernel Prior for Blind Image Deblurring](https://mlsanity.com/paper/2504.14664/) (2025)
- [Generative Latent Kernel Modeling for Blind Motion Deblurring](https://mlsanity.com/paper/2507.09285/) (2025)
- [Leveraging Phase Information to Boost Unrolled Network Learning for Image Deblurring](https://mlsanity.com/paper/2607.00251/) (2026)
- [BAM! Bayesian Anything Model: a foundation model for generative computational imaging](https://mlsanity.com/paper/2609.39660/) (2026)

## Abstract (arXiv)

In recent years, the removal of motion blur in photographs has seen impressive progress in the hands of deep learning-based methods, trained to map directly from blurry to sharp images. For this reason, approaches that explicitly use a forward degradation model received significantly less attention. However, a well-defined specification of the blur genesis, as an intermediate step, promotes the generalization and explainability of the method. Towards this goal, we propose a learning-based motion deblurring method based on dense non-uniform motion blur estimation followed by a non-blind deconvolution approach. Specifically, given a blurry image, a first network estimates the dense per-pixel motion blur kernels using a lightweight representation composed of a set of image-adaptive basis motion kernels and the corresponding mixing coefficients. Then, a second network trained jointly with the first one, unrolls a non-blind deconvolution method using the motion kernel field estimated by the first network. The model-driven aspect is further promoted by training the networks on sharp/blurry pairs synthesized according to a convolution-based, non-uniform motion blur degradation model. Qualitative and quantitative evaluation shows that the kernel prediction network produces accurate motion blur estimates, and that the deblurring pipeline leads to restorations of real blurred images that are competitive or superior to those obtained with existing end-to-end deep learning-based methods. Code and trained models are available at https://github.com/GuillermoCarbajal/J-MKPD/.