让红外图像超分辨更真实，提升下游任务性能
FaithIR: Rethinking Infrared Image Super-Resolution from Perceptual Sharpness to Task Relevant Fidelity
- 分块条件+像素级重建，结构引导保真
- 跨数据集泛化强，检测与分割性能优
- 重在真实结构保留，非单纯追求清晰度
红外图像超分辨（IISR）对目标检测、语义分割等下游任务至关重要。现有方法常产生人工纹理、过度锐化的边缘和虚假高频细节，扭曲真实的热结构与语义信息。为此，我们提出FaithIR框架，通过分块级条件分支捕捉全局热与结构信息，结合像素级修复分支在结构引导下进行密集局部重建。整个过程直接在像素域完成，有效保留红外特有结构与任务相关特征。在FLIR-IISR、M3FD和FMB数据集上的实验表明，该方法具有强重建保真度、跨数据集泛化能力，且在目标检测与语义分割任务中表现更优。结果表明，对于可靠机器感知而言，保持红外结构真实性比单纯追求视觉锐度更为重要。
原文摘要 · Abstract (English)
Infrared image super-resolution (IISR) is important for downstream tasks such as object detection and semantic segmentation. Existing IISR methods often produce artificial textures, over-sharpened edges, and spurious high-frequency details that distort authentic thermal structures and semantic information. To address this issue, we propose FaithIR, a faithful infrared super-resolution framework for reliable machine perception. FaithIR consists of a patch-level conditioning branch that captures global thermal and structural information and a pixel-level restoration branch that performs dense local reconstruction under structural guidance. The entire restoration process is performed directly in the pixel domain to preserve infrared-specific structures and task-relevant information. Extensive experiments on FLIR-IISR, M3FD, and FMB demonstrate strong reconstruction fidelity, cross-dataset generalization, and superior performance in object detection and semantic segmentation. These results show that demonstrate that preserving faithful infrared structure preservations is more important for reliable machine perception than merely pursuing perceptual sharpness alone.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。