# Neural Blind Deconvolution Using Deep Priors

arXiv: https://arxiv.org/abs/1908.02197 · HTML: https://mlsanity.com/paper/1908.02197/

## Key facts

- Cited by 113 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2019.

## Built on by (most cited first, 30 of 113)

- [Parallel Diffusion Models of Operator and Image for Blind Inverse Problems](https://mlsanity.com/paper/2211.10656/) (2022)
- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [Flow-based Kernel Prior with Application to Blind Super-Resolution](https://mlsanity.com/paper/2103.15977/) (2021)
- [Deblurring 3D Gaussian Splatting](https://mlsanity.com/paper/2401.00834/) (2024)
- [DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models](https://mlsanity.com/paper/2405.16749/) (2024)
- [GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration](https://mlsanity.com/paper/2301.12686/) (2023)
- [Explore Image Deblurring via Blur Kernel Space](https://mlsanity.com/paper/2104.00317/) (2021)
- [Early Stopping for Deep Image Prior](https://mlsanity.com/paper/2112.06074/) (2021)
- [Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution](https://mlsanity.com/paper/2309.00287/) (2023)
- [Learning Degradation Representations for Image Deblurring](https://mlsanity.com/paper/2208.05244/) (2022)
- [Blind Image Restoration via Fast Diffusion Inversion](https://mlsanity.com/paper/2405.19572/) (2024)
- [Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel](https://mlsanity.com/paper/2107.00986/) (2021)
- [MC-Blur: A Comprehensive Benchmark for Image Deblurring](https://mlsanity.com/paper/2112.00234/) (2021)
- [KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution](https://mlsanity.com/paper/2209.10305/) (2022)
- [Optical Aberration Correction in Postprocessing using Imaging Simulation](https://mlsanity.com/paper/2305.05867/) (2023)
- [Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring](https://mlsanity.com/paper/2104.12665/) (2021)
- [End-to-end Alternating Optimization for Blind Super Resolution](https://mlsanity.com/paper/2105.06878/) (2021)
- [Self-Supervised Image Restoration with Blurry and Noisy Pairs](https://mlsanity.com/paper/2211.07317/) (2022)
- [Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time](https://mlsanity.com/paper/2303.15043/) (2023)
- [Robust Gaussian Splatting](https://mlsanity.com/paper/2404.04211/) (2024)
- [Self-Validation: Early Stopping for Single-Instance Deep Generative Priors](https://mlsanity.com/paper/2110.12271/) (2021)
- [A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution](https://mlsanity.com/paper/2404.15620/) (2024)
- [Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior](https://mlsanity.com/paper/2210.05361/) (2022)
- [Learning Image-Adaptive Codebooks for Class-Agnostic Image Restoration](https://mlsanity.com/paper/2306.06513/) (2023)
- [Scale-Equivariant Imaging: Self-Supervised Learning for Image Super-Resolution and Deblurring](https://mlsanity.com/paper/2312.11232/) (2023)
- [SinIR: Efficient General Image Manipulation with Single Image Reconstruction](https://mlsanity.com/paper/2106.07140/) (2021)
- [Deep Hybrid Self-Prior for Full 3D Mesh Generation](https://mlsanity.com/paper/2108.08017/) (2021)
- [Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Prior](https://mlsanity.com/paper/2401.00825/) (2024)
- [TurbuGAN: An Adversarial Learning Approach to Spatially-Varying Multiframe Blind Deconvolution with Applications to Imaging Through Turbulence](https://mlsanity.com/paper/2203.06764/) (2022)
- [BSRAW: Improving Blind RAW Image Super-Resolution](https://mlsanity.com/paper/2312.15487/) (2023)

## Abstract (arXiv)

Blind deconvolution is a classical yet challenging low-level vision problem with many real-world applications. Traditional maximum a posterior (MAP) based methods rely heavily on fixed and handcrafted priors that certainly are insufficient in characterizing clean images and blur kernels, and usually adopt specially designed alternating minimization to avoid trivial solution. In contrast, existing deep motion deblurring networks learn from massive training images the mapping to clean image or blur kernel, but are limited in handling various complex and large size blur kernels. To connect MAP and deep models, we in this paper present two generative networks for respectively modeling the deep priors of clean image and blur kernel, and propose an unconstrained neural optimization solution to blind deconvolution. In particular, we adopt an asymmetric Autoencoder with skip connections for generating latent clean image, and a fully-connected network (FCN) for generating blur kernel. Moreover, the SoftMax nonlinearity is applied to the output layer of FCN to meet the non-negative and equality constraints. The process of neural optimization can be explained as a kind of "zero-shot" self-supervised learning of the generative networks, and thus our proposed method is dubbed SelfDeblur. Experimental results show that our SelfDeblur can achieve notable quantitative gains as well as more visually plausible deblurring results in comparison to state-of-the-art blind deconvolution methods on benchmark datasets and real-world blurry images. The source code is available at https://github.com/csdwren/SelfDeblur