自扩散驱动的盲成像
Self-Diffusion Driven Blind Imaging
把预训练扩散模型的去噪先验换成从纯噪声出发的自扩散反向过程，在无需任何训练数据的情况下联合迭代优化清晰图像与未知模糊核，可直接迁移到盲去模糊、盲去卷积等病态逆问题。
原文依据 DeblurSDI formulates blind image recovery as an iterative reverse self-diffusion process that begins from pure noise
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论光学成像系统由于衍射极限、镜头制造公差、装配失准以及其他物理约束而本质上并不完美。此外，不可避免的相机抖动与物体运动还会在采集过程中引入非理想的退化。这些像差与运动引起的变化通常是未知的、难以测量的，并且在实际中建模或标定的代价很高。盲逆问题提供了一条有前景的路径，即联合估计潜变量图像与未知退化核。然而，现有方法常常面临收敛不稳定、先验表达能力有限以及对超参数敏感等问题。受近期自扩散进展的启发，我们提出 DeblurSDI，一个无需预训练的零样本、自监督盲成像框架。DeblurSDI 将盲图像恢复建模为从纯噪声出发的迭代反向自扩散过程，逐步同时精化清晰图像与模糊核。在光学像差与运动模糊联合作用下的广泛实验表明，DeblurSDI 以显著优势持续优于其他方法。
英文原文摘要 1185 字符
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.