HiDRA：面向红外视觉增强的分层退化表征与生成先验自适应
HiDRA: Hierarchical Degradation Representation and Adaptation with Generative Priors for Enhancing Infrared Vision
把退化模式显式建模成可解耦的表征，再用它去条件化生成模型的参数微调，这个「退化表征→参数自适应」的范式可以直接迁移到低光照、去噪、去模糊等复合退化复原任务上，尤其是可见光预训练扩散先验跨域适配到非可见光成像的场景。
原文依据 decompose the enhancement procedure into degradation representation estimation and generative model fine-tuning
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论热红外（TIR）成像能够在恶劣条件下实现鲁棒感知。然而，受传感器限制与环境动态变化影响，它常常遭受复杂退化（例如固定模式噪声与低分辨率）。现有方法无论是传统方法还是基于学习的方法，在复合且多变的退化下都容易失效。预训练生成模型在缓解退化方面展现出强大能力，但缺乏将可见光生成先验适配到 TIR 特有特性的有效工具。为克服这些挑战，我们提出分层退化表征与自适应（HiDRA）框架，将增强过程分解为退化表征估计与生成模型微调两部分。退化表征估计旨在解耦 TIR 退化模式，并以此引导热图像增强的参数自适应。此外，我们引入分层自适应方案，聚合不同退化层级上的学习，进一步提升多种场景下的鲁棒性。跨多种退化类型与程度的实验证明了本方法的鲁棒性，并进一步验证了其在下游任务上的有效性。代码见 https://github.com/Zihang-Chen/HiDRA。
英文原文摘要 1301 字符
Thermal infrared (TIR) imaging enables robust perception in adverse conditions. However, it often suffers from complex degradations (e.g., fixed-pattern noise and low-resolution) due to sensor limitations and environmental dynamics. Existing methods, whether traditional or learning-based, easily fail under composite and varying degradation. Pre-trained generative models showcase powerful capabilities for alleviating degradations but lack effective tools to adapt visible generative priors to TIR-specific characteristics. To overcome these challenges, we propose a Hierarchical Degradation Representation and Adaptation (HiDRA) framework to decompose the enhancement procedure into degradation representation estimation and generative model fine-tuning. The degradation representation estimation aims to disentangle TIR degradation patterns, which then guide the parameter adaptation for thermal image enhancement. Additionally, we introduce a hierarchical adaptation solution that aggregates learning across varying degradation levels, further improving robustness under various scenarios. Experiments across diverse types and degrees demonstrate the robustness of our approach and further validate its effectiveness on downstream tasks. Code is available at https://github.com/Zihang-Chen/HiDRA.