基于提示条件信息瓶颈的极端盲图像复原
Extreme Blind Image Restoration via Prompt-Conditioned Information Bottleneck
AI总结：
针对极端盲图像复原中严重复合退化导致的域差距大、复原易出伪影丢细节的问题，提出基于信息瓶颈的分解式框架，通过投影器将极低质量图像映射至中间低退化流形，再用现成冻结BIR模型复原，支持即插即用增强现有模型且无需微调。
摘要：
盲图像复原（Blind Image Restoration, BIR）方法已取得显著成效，但在面对极端盲图像复原（Extreme Blind Image Restoration, EBIR）任务时表现不佳——这类任务的输入存在超出其训练范围的严重、复合退化。由于存在巨大的域差距，直接学习极低质量（extremely low-quality, ELQ）图像到高质量（high-quality, HQ）图像的映射极具挑战，往往会产生不自然的伪影并丢失细节。为解决这一问题，我们提出一种新型框架，将难以处理的ELQ到HQ复原过程进行分解。我们首先学习一个投影器，将ELQ图像映射到中间的、退化程度更低的LQ流形上，随后使用冻结的现成BIR模型将该中间图像复原为HQ图像。我们的方法以信息论为基础；提出将图像复原视为信息瓶颈问题的全新视角，并推导出一个有理论支撑的目标函数来训练投影器。该损失函数通过平衡低质量重建项与高质量先验匹配项，有效稳定了训练过程。我们的框架支持推理阶段提示优化的“单次前向预测（Look Forward Once, LFO）”机制，且无需微调即可即插即用增强现有图像复原模型。我们在严重退化场景下开展了大量实验，对所提方法的有效性进行了全面分析。
英文摘要：
Blind Image Restoration (BIR) methods have achieved remarkable success but falter when faced with Extreme Blind Image Restoration (EBIR), where inputs suffer from severe, compounded degradations beyond their training scope. Directly learning a mapping from extremely low-quality (ELQ) to high-quality (HQ) images is challenging due to the massive domain gap, often leading to unnatural artifacts and loss of detail. To address this, we propose a novel framework that decomposes the intractable ELQ-to-HQ restoration process. We first learn a projector that maps an ELQ image onto an intermediate, less-degraded LQ manifold. This intermediate image is then restored to HQ using a frozen, off-the-shelf BIR model. Our approach is grounded in information theory; we provide a novel perspective of image restoration as an Information Bottleneck problem and derive a theoretically-driven objective to train our projector. This loss function effectively stabilizes training by balancing a low-quality reconstruction term with a high-quality prior-matching term. Our framework enables Look Forward Once (LFO) for inference-time prompt refinement, and supports plug-and-play strengthening of existing image restoration models without need for finetuning. Extensive experiments under severe degradation regimes provide a thorough analysis of the effectiveness of our work.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
