Image deblurring has advanced rapidly with deep learning, yet most methods exhibit poor generalization beyond their training datasets, with performance dropping significantly in real-world scenarios. Our analysis shows this limitation stems from two factors: datasets face an inherent trade-off between realism and coverage of diverse blur patterns, and algorithmic designs remain restrictive, as pixel-wise losses drive models toward local detail recovery while overlooking structural and semantic consistency, whereas diffusion-based approaches, though perceptually strong, still fail to generalize when trained on narrow datasets with simplistic strategies. Through systematic investigation, we identify blur pattern diversity as the decisive factor for robust generalization and propose Blur Pattern Pretraining (BPP), which acquires blur priors from simulation datasets and transfers them through joint fine-tuning on real data. We further introduce Motion and Semantic Guidance (MoSeG) to strengthen blur priors under severe degradation, and integrate it into GLOWDeblur, a Generalizable reaL-wOrld lightWeight Deblur model that combines convolution-based pre-reconstruction & domain alignment module with a lightweight diffusion backbone. Extensive experiments on six widely-used benchmarks and two real-world datasets validate our approach, confirming the importance of blur priors for robust generalization and demonstrating that the lightweight design of GLOWDeblur ensures practicality in real-world applications. The project page is available at https://vegdog007.github.io/GLOWDeblur_Website/.

翻译：图像去模糊技术随着深度学习的发展取得了快速进步，然而大多数方法在其训练数据集之外表现出较差的泛化能力，在真实场景中性能显著下降。我们的分析表明，这一局限性源于两个因素：数据集在真实性与多样化模糊模式覆盖之间存在固有的权衡；算法设计仍具局限性，因为逐像素损失驱使模型倾向于局部细节恢复而忽视了结构与语义一致性，而基于扩散的方法虽然在感知质量上表现强劲，但在使用简单策略的狭窄数据集上训练时仍无法实现泛化。通过系统性研究，我们确认模糊模式多样性是实现鲁棒泛化的决定性因素，并提出了模糊模式预训练（BPP），该方法从仿真数据集中获取模糊先验，并通过在真实数据上的联合微调进行迁移。我们进一步引入运动与语义引导（MoSeG），以在严重退化条件下增强模糊先验，并将其集成到GLOWDeblur中——这是一个可泛化的真实世界轻量级去模糊模型，结合了基于卷积的预重建与域对齐模块以及轻量级扩散主干网络。在六个广泛使用的基准数据集和两个真实世界数据集上的大量实验验证了我们的方法，证实了模糊先验对鲁棒泛化的重要性，并证明了GLOWDeblur的轻量级设计确保了其在真实世界应用中的实用性。项目页面位于 https://vegdog007.github.io/GLOWDeblur_Website/。