Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset
迈向真实世界红外图像超分辨率:一个统一的自回归框架和基准数据集
机构 * School of Computer Science, Northwestern Polytechnical University(西北工业大学计算机学院) ; School of Software Technology & DUT-RU International School of ISE, Dalian University of Technology(大连理工大学软件学院及DUT-RU国际信息工程学院) ; School of Computer Science, Zhejiang University(浙江大学计算机学院) ; College of Information Science and Technology, Dalian Maritime University(大连海事大学信息科学与技术学院)
专题命中 红外-可见光融合 :infrared and visible(abstract);分类 cs.CV
AI总结 本文提出Real-IISR框架和FLIR-IISR数据集,通过热-结构引导的自回归方法提升真实世界红外图像超分辨率性能。
Comments This paper was accepted by CVPR 2026