# Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior

arXiv: https://arxiv.org/abs/2210.05361 · HTML: https://mlsanity.com/paper/2210.05361/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 50 references that are in the map.
- First posted on arXiv 9 Oct 2022.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Learning Deep CNN Denoiser Prior for Image Restoration](https://mlsanity.com/paper/1704.03264/) (2017)
- [Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal](https://mlsanity.com/paper/1503.00593/) (2015)
- [Deep Generalized Unfolding Networks for Image Restoration](https://mlsanity.com/paper/2204.13348/) (2022)
- ["Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors](https://mlsanity.com/paper/1812.00467/) (2018)
- [Neural Blind Deconvolution Using Deep Priors](https://mlsanity.com/paper/1908.02197/) (2019)
- [DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring](https://mlsanity.com/paper/2103.09962/) (2021)
- [Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution](https://mlsanity.com/paper/1611.06495/) (2016)
- [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)

## Built on by (most cited first, 14 of 14)

- [Prompt-In-Prompt Learning for Universal Image Restoration](https://mlsanity.com/paper/2312.05038/) (2023)
- [Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration](https://mlsanity.com/paper/2411.01656/) (2024)
- [Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration](https://mlsanity.com/paper/2405.02843/) (2024)
- [FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring](https://mlsanity.com/paper/2510.01641/) (2025)
- [Gyro-based Neural Single Image Deblurring](https://mlsanity.com/paper/2404.00916/) (2024)
- [BaryIR: Learning Multi-Source Unified Representation in Continuous Barycenter Space for Generalizable All-in-One Image Restoration](https://mlsanity.com/paper/2505.21637/) (2025)
- [Reblurring-Guided Single Image Defocus Deblurring: A Learning Framework with Misaligned Training Pairs](https://mlsanity.com/paper/2409.17792/) (2024)
- [Learning Deblurring Texture Prior from Unpaired Data with Diffusion Model](https://mlsanity.com/paper/2507.13599/) (2025)
- [Unsupervised Methods for Video Quality Improvement: A Survey of Restoration and Enhancement Techniques](https://mlsanity.com/paper/2507.08375/) (2025)
- [Res-U2Net: Untrained Deep Learning for Phase Retrieval and Image Reconstruction](https://mlsanity.com/paper/2404.06657/) (2024)
- [Generative Latent Kernel Modeling for Blind Motion Deblurring](https://mlsanity.com/paper/2507.09285/) (2025)
- [BluRef: Unsupervised Image Deblurring with Dense-Matching References](https://mlsanity.com/paper/2603.14176/) (2026)
- [HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation](https://mlsanity.com/paper/2605.13581/) (2026)
- [Physen-Noise2Noise: Physics-Guided Self-Supervised Defocus Deblurring with Bias Correction under Low-Light Conditions](https://mlsanity.com/paper/2605.24590/) (2026)

## Abstract (arXiv)

Non-blind deblurring methods achieve decent performance under the accurate blur kernel assumption. Since the kernel uncertainty (i.e. kernel error) is inevitable in practice, semi-blind deblurring is suggested to handle it by introducing the prior of the kernel (or induced) error. However, how to design a suitable prior for the kernel (or induced) error remains challenging. Hand-crafted prior, incorporating domain knowledge, generally performs well but may lead to poor performance when kernel (or induced) error is complex. Data-driven prior, which excessively depends on the diversity and abundance of training data, is vulnerable to out-of-distribution blurs and images. To address this challenge, we suggest a dataset-free deep residual prior for the kernel induced error (termed as residual) expressed by a customized untrained deep neural network, which allows us to flexibly adapt to different blurs and images in real scenarios. By organically integrating the respective strengths of deep priors and hand-crafted priors, we propose an unsupervised semi-blind deblurring model which recovers the latent image from the blurry image and inaccurate blur kernel. To tackle the formulated model, an efficient alternating minimization algorithm is developed. Extensive experiments demonstrate the favorable performance of the proposed method as compared to data-driven and model-driven methods in terms of image quality and the robustness to the kernel error.