Abstract: Existing image super-resolution networks are mostly designed for visible light images, with relatively fewer studies focusing on infrared image super-resolution, and most of them simply adopt methods from visible light image super-resolution. In response to the low resolution and blurred edges of infrared images, this paper proposes a gradient-guided infrared image super-resolution reconstruction network. The network fully utilizes the gradient information in low-resolution infrared images, fusing the gradient map with the extracted features, resulting in a high-resolution image with clearer edges and higher contrast. The experimental results of the comparative and ablation studies demonstrate that the proposed method in this paper outperforms other comparative methods in infrared image super-resolution reconstruction, generating high-resolution images of higher quality.