Una red de mejora de percepción híbrida ligera para la superresolución de imágenes infrarrojas

Infrared image super-resolution (SR) remains a challenging task due to inherent limitations in existing approaches: convolutional neural network (CNN)-based approaches struggle with long-range dependency modeling, whereas transformer-based approaches are computationally expensive and tend to overlook fine local details. To address these issues, we propose a novel hybrid perception enhancement network (HPEN). Its core component is a hybrid perception enhancement block (HPEB), which effectively combines a token aggregation block (TAB) for global context modeling, a multi-scale feature enhancement block (MFEB) for local detail extraction, and a convolutional layer for feature refinement. Extensive experimental results demonstrate that the proposed HPEN achieves leading performance among compared methods. For the challenging [Formula: see text] SR task, it attains the best PSNR and SSIM values among the evaluated lightweight SR approaches, while demonstrating remarkable efficiency advantages. Specifically, compared to HiT-SR, HPEN reduces FLOPs by 42.9%, uses only 9.4% of the GPU memory usage, and delivers a [Formula: see text] faster inference speed. The code is available at https://github.com/smilenorth1/HPEN-main.