迈向真实世界红外图像超分辨率：统一自回归框架与基准数据集
Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset
提出热结构引导的自回归框架与条件自适应码本，可迁移到其他真实退化下的底层视觉任务（如低光增强、去模糊），其热序一致性损失为物理约束融入复原模型提供思路。
原文依据 we propose Real-IISR, a unified autoregressive framework for real-world IISR that progressively reconstructs fine-grained thermal structures and clear backgrounds in a scale-by-scale manner
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论真实条件下的红外图像超分辨率（IISR）是一项具有实际意义但鲜有研究的任务。已有工作通常在模拟数据集上训练和评估，或忽略了红外与可见光成像之间的内在差异。然而在实践中，真实红外图像受到光学与传感退化的耦合影响，这些退化共同损害了结构锐度和热保真度。为应对这些挑战，我们提出Real-IISR，一个面向真实世界IISR的统一自回归框架，通过热结构引导的视觉自回归以逐尺度方式渐进重建细粒度热结构和清晰背景。具体而言，热结构引导模块编码热先验以缓解热辐射与结构边缘之间的不匹配。由于非均匀退化通常引入量化偏差，Real-IISR采用条件自适应码本，基于退化感知的热先验动态调制离散表示。此外，热序一致性损失强制温度与像素强度之间的单调关系，确保相对亮度顺序而非绝对值，以在空间错位和热漂移下保持物理一致性。我们构建了FLIR-IISR，一个通过自动对焦变化和运动模糊获取配对低分辨率-高分辨率红外图像的真实世界IISR数据集。大量实验证明了Real-IISR的优异性能，为真实世界IISR和基准测试提供了统一基础。数据集和代码可在https://github.com/JZD151/Real-IISR获取。
英文原文摘要 1684 字符
Infrared image super-resolution (IISR) under real-world conditions is a practically significant yet rarely addressed task. Pioneering works are often trained and evaluated on simulated datasets or neglect the intrinsic differences between infrared and visible imaging. In practice, however, real infrared images are affected by coupled optical and sensing degradations that jointly deteriorate both structural sharpness and thermal fidelity. To address these challenges, we propose Real-IISR, a unified autoregressive framework for real-world IISR that progressively reconstructs fine-grained thermal structures and clear backgrounds in a scale-by-scale manner via thermal-structural guided visual autoregression. Specifically, a Thermal-Structural Guidance module encodes thermal priors to mitigate the mismatch between thermal radiation and structural edges. Since non-uniform degradations typically induce quantization bias, Real-IISR adopts a Condition-Adaptive Codebook that dynamically modulates discrete representations based on degradation-aware thermal priors. Also, a Thermal Order Consistency Loss enforces a monotonic relation between temperature and pixel intensity, ensuring relative brightness order rather than absolute values to maintain physical consistency under spatial misalignment and thermal drift. We build FLIR-IISR, a real-world IISR dataset with paired LR-HR infrared images acquired via automated focus variation and motion-induced blur. Extensive experiments demonstrate the promising performance of Real-IISR, providing a unified foundation for real-world IISR and benchmarking. The dataset and code are available at: https://github.com/JZD151/Real-IISR.