# End-to-end Interpretable Learning of Non-blind Image Deblurring

arXiv: https://arxiv.org/abs/2007.01769 · HTML: https://mlsanity.com/paper/2007.01769/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2020.

## Built on by (most cited first, 16 of 16)

- [DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring](https://mlsanity.com/paper/2103.09962/) (2021)
- [Fast Two-step Blind Optical Aberration Correction](https://mlsanity.com/paper/2208.00950/) (2022)
- [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)
- [Deep Model-Based Super-Resolution with Non-uniform Blur](https://mlsanity.com/paper/2204.10109/) (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)
- [PnP-ReG: Learned Regularizing Gradient for Plug-and-Play Gradient Descent](https://mlsanity.com/paper/2204.13940/) (2022)
- [On Adversarial Robustness of Deep Image Deblurring](https://mlsanity.com/paper/2210.02502/) (2022)
- [Deep Richardson-Lucy Deconvolution for Low-Light Image Deblurring](https://mlsanity.com/paper/2308.05543/) (2023)
- [Learning to Deblur Polarized Images](https://mlsanity.com/paper/2402.18134/) (2024)
- [Learning to Jointly Deblur, Demosaick and Denoise Raw Images](https://mlsanity.com/paper/2104.06459/) (2021)
- [Deep Camera Obscura: An Image Restoration Pipeline for Lensless Pinhole Photography](https://mlsanity.com/paper/2108.05563/) (2021)
- [Learning Discriminative Shrinkage Deep Networks for Image Deconvolution](https://mlsanity.com/paper/2111.13876/) (2021)
- [Leveraging Classic Deconvolution and Feature Extraction in Zero-Shot Image Restoration](https://mlsanity.com/paper/2310.02097/) (2023)
- [Parallel Backpropagation for Inverse of a Convolution with Application to Normalizing Flows](https://mlsanity.com/paper/2410.14634/) (2024)
- [RealRep: Generalized SDR-to-HDR Conversion via Attribute-Disentangled Representation Learning](https://mlsanity.com/paper/2505.07322/) (2025)

## Abstract (arXiv)

Non-blind image deblurring is typically formulated as a linear least-squares problem regularized by natural priors on the corresponding sharp picture's gradients, which can be solved, for example, using a half-quadratic splitting method with Richardson fixed-point iterations for its least-squares updates and a proximal operator for the auxiliary variable updates. We propose to precondition the Richardson solver using approximate inverse filters of the (known) blur and natural image prior kernels. Using convolutions instead of a generic linear preconditioner allows extremely efficient parameter sharing across the image, and leads to significant gains in accuracy and/or speed compared to classical FFT and conjugate-gradient methods. More importantly, the proposed architecture is easily adapted to learning both the preconditioner and the proximal operator using CNN embeddings. This yields a simple and efficient algorithm for non-blind image deblurring which is fully interpretable, can be learned end to end, and whose accuracy matches or exceeds the state of the art, quite significantly, in the non-uniform case.