发表机构
Tongji University; Nanyang Technological University; The University of Hong Kong（同济大学; 南洋理工大学; 香港大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对真实世界热成像超分辨率中合成与真实退化域差距问题，提出由GPT-6 Astra引导的AstraSR方法，利用生成参考与多损失监督，在热清晰度和结构连贯性上超越现有方法。
AI 中文摘要
真实世界的热成像超分辨率（SR）受限于传感器分辨率有限，以及难以获得对应的高分辨率（HR）观测用于直接监督模型。传统SR方法通常将带有真实世界退化（degradation）的捕获热图像视为HR参考，并施加预定义退化来生成合成低分辨率（LR）输入，以此构建训练对。这种构建方式不仅在合成LR观测与捕获LR观测之间引入了域差距，而且还将采集退化保留在监督信号中。为解决此问题，我们提出AstraSR，一种由GPT-6 Astra引导的真实世界热成像SR方法。GPT-6 Astra是一种前沿的多模态生成模型，具备涌现性和变革性的视觉能力。具体而言，我们通过使用捕获的LR热图像来条件化基于GPT的HR参考，构建了一个图像对数据集。我们开发了一种直接生成监督策略，该策略从配对的捕获热输入与GPT生成的HR参考中学习。像素损失、梯度损失和感知损失共同监督从生成参考中迁移强度模式、结构边界和视觉细节。与七种现有最先进的真实世界SR方法的定性比较显示，在热场景中，AstraSR具有连续的物体轮廓、清晰的结构边界和平滑的强度过渡。这些结果表明，AstraSR在热清晰度和结构连贯性方面均优于现有的真实世界SR方法。
英文摘要
Real-world thermal super-resolution (SR) is constrained by limited sensor resolution and the difficulty of obtaining corresponding high-resolution (HR) observations for direct model supervision. Conventional SR methods typically construct training pairs by treating captured thermal images with real-world degradations as HR references and applying predefined degradation to generate synthetic low-resolution (LR) inputs. Such a construction not only introduces a domain gap between synthetic and captured LR observations but also retains acquisition degradations in the supervision. To address this issue, we propose AstraSR, a real-world thermal SR method guided by GPT-6 Astra, a frontier multimodal generative model endowed with emergent and transformative visual capabilities. Specifically, we construct a dataset of image pairs by using captured LR thermal images to condition GPT-based HR reference. We develop a direct generative supervision strategy that learns from captured thermal inputs paired with GPT-generated HR references. Pixel, gradient, and perceptual losses jointly supervise the transfer of intensity patterns, structural boundaries, and visual details from the generated references. Qualitative comparisons with seven existing state-of-the-art real-world SR methods show continuous object contours, distinct structural boundaries, and smooth intensity transitions in the thermal scenes. These results demonstrate that AstraSR outperforms existing real-world SR methods in both thermal clarity and structural coherence.
