Self-Diffusion Driven Blind Imaging
This addresses the challenge of unknown degradations in optical imaging for applications like photography or microscopy, though it appears incremental as it builds on self-diffusion advances.
The paper tackles the problem of blind image recovery from unknown optical aberrations and motion blur by proposing DeblurSDI, a zero-shot self-supervised framework that jointly estimates the latent image and blur kernel through iterative reverse self-diffusion, achieving substantial performance gains over other methods in experiments.
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.