Self-Diffusion Driven Blind Imaging

TL;DR

DeblurSDI is a zero-shot, self-supervised blind imaging method that iteratively refines images and kernels from noise, effectively handling optical aberrations and motion blur without pre-training.

Contribution

It introduces DeblurSDI, a novel self-diffusion based framework for blind image restoration that requires no pre-training and improves stability and accuracy.

Findings

Outperforms existing blind deblurring methods significantly

Handles combined optical aberrations and motion blur effectively

Requires no pre-training, enabling zero-shot application

Abstract

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.