# Self-Diffusion Driven Blind Imaging

arXiv: https://arxiv.org/abs/2510.27439 · HTML: https://mlsanity.com/paper/2510.27439/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 36 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 14 of 14)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal](https://mlsanity.com/paper/1503.00593/) (2015)
- ["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)
- [Handheld Multi-Frame Super-Resolution](https://mlsanity.com/paper/1905.03277/) (2019)
- [Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution](https://mlsanity.com/paper/2309.00287/) (2023)
- [Phase-only Image Based Kernel Estimation for Single-image Blind Deblurring](https://mlsanity.com/paper/1811.10185/) (2018)
- [An Analysis and Implementation of the HDR+ Burst Denoising Method](https://mlsanity.com/paper/2110.09354/) (2021)
- [Self-diffusion for Solving Inverse Problems](https://mlsanity.com/paper/2510.21417/) (2025)
- [Blind Image Deblurring with FFT-ReLU Sparsity Prior](https://mlsanity.com/paper/2406.08344/) (2024)
- [Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Sampling](https://mlsanity.com/paper/2510.09676/) (2025)

## Abstract (arXiv)

Optical imaging systems are inherently imperfect due to diffraction limits, lens manufacturing tolerances, assembly misalignment, and other physical constraints. In addition, unavoidable camera shake and object motion further introduce non-ideal degradations during acquisition. These aberrations and motion-induced variations are typically unknown, difficult to measure, and costly to model or calibrate in practice. Blind inverse problems offer a promising direction by jointly estimating both the latent image and the unknown degradation kernel. However, existing approaches often suffer from convergence instability, limited prior expressiveness, and sensitivity to hyperparameters. Inspired by recent advances in self-diffusion, we propose DeblurSDI, a zero-shot, self-supervised blind imaging framework that requires no pre-training. DeblurSDI formulates blind image recovery as an iterative reverse self-diffusion process that begins from pure noise and progressively refines both the sharp image and the blur kernel. Extensive experiments on combined optical aberrations and motion blur demonstrate that DeblurSDI consistently outperforms other methods by a substantial margin.