 This paper proposes a novel approach to infrared image colorization using a conditional generative adversarial network, CGAN. It combines a multi-scale feature extraction module with an attention mechanism to improve the semantic understanding of the generator and discriminator. Additionally, it incorporates a channel attention and spatial attention module to further enhance the performance of the discriminator. The proposed method achieves a peak signal-to-noise ratio, PSNR, of 16.5342 dB and a structural similarity index, SSIM, of 0.6385 on an RGBNIR, red, green, blue-near infrared testing dataset, representing a 5% and 13% improvement over the original CGAN network, respectively. This article was authored by EBA AI, Xiaoxilu, Huyangzhai, and others. We are article.tv, links in the description below.