发表机构
DxO Labs; LTCI, Télécom Paris, IP Paris（DxO Labs; LTCI，巴黎电信学院，巴黎理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出基于扩散模型的SuperSharpen盲去模糊方法，通过模糊度量可控调整复原强度，经实验验证其在合成与真实模糊上的感知质量及可控性优于对比策略
AI 中文摘要
相机成像过程中会因光学系统、传感器或低级处理步骤产生多种退化，本文针对专业摄影中的盲去模糊问题，目标是在未知各向同性模糊且不了解退化情况的前提下进行图像复原。在这类丢失高频信息的逆问题中，生成模型难以生成既符合输入又具照片真实感的细节。本文提出SuperSharpen，一种基于扩散模型的盲去模糊方法，通过模糊度量提供对复原强度的显式控制。我们对比了两种条件策略：冻结主干上的ControlNet风格适配器，以及对扩散先验的全微调。实验表明，微调能在更少幻觉细节的情况下实现更好的保真度，我们在合成和真实世界模糊上验证了该方法，其在感知质量和可控复原强度上均有提升。
英文摘要
Image acquisition with a camera involves several degradations due to the optical system, sensor, or low-level processing steps. We address blind deblurring in professional photography: we aim to invert unknown isotropic blur without knowledge of the degradation kernel. For such inverse problems,where some high-frequency information is lost, it is challenging to use generative models to produce details that are both photo-realistic and faithful to the input. We propose SuperSharpen, a diffusion-based blind deblurring method offering explicit control over restoration strength through a blur measure. We compare two conditioning strategies: a ControlNet-style adapter on a frozen backbone, and full finetuning of the diffusion prior. Our experiments show that finetuning achieves better fidelity with fewer hallucinated details. We validate our approach on synthetic and real-world blur, demonstrating improved perceptual quality and controllable restoration strength.
Comments6 pages, 5 figures, 1 table. Accepted to IEEE ICIP 2026
