Jia Ruiming, Chen Xin, Li Tong, Cui Jiali
School of Information Science and Technology, North China University of Technology, Beijing 100144, China.
Sensors (Basel). 2022 Mar 9;22(6):2119. doi: 10.3390/s22062119.
Infrared image simulation is challenging because it is complex to model. To estimate the corresponding infrared image directly from the visible light image, we propose a three-level refined light-weight generative adversarial network with cascaded guidance (V2T-GAN), which can improve the accuracy of the infrared simulation image. V2T-GAN is guided by cascading auxiliary tasks and auxiliary information: the first-level adversarial network uses semantic segmentation as an auxiliary task, focusing on the structural information of the infrared image; the second-level adversarial network uses the grayscale inverted visible image as the auxiliary task to supplement the texture details of the infrared image; the third-level network obtains a sharp and accurate edge by adding auxiliary information of the edge image and a displacement network. Experiments on the public dataset Multispectral Pedestrian Dataset demonstrate that the structure and texture features of the infrared simulation image obtained by V2T-GAN are correct, and outperform the state-of-the-art methods in objective metrics and subjective visualization effects.
红外图像模拟具有挑战性，因为其建模复杂。为了直接从可见光图像估计相应的红外图像，我们提出了一种具有级联引导的三级精炼轻量级生成对抗网络（V2T-GAN），它可以提高红外模拟图像的准确性。V2T-GAN由级联辅助任务和辅助信息引导：第一级对抗网络使用语义分割作为辅助任务，专注于红外图像的结构信息；第二级对抗网络使用灰度反转的可见光图像作为辅助任务，以补充红外图像的纹理细节；第三级网络通过添加边缘图像的辅助信息和位移网络来获得清晰准确的边缘。在公共数据集多光谱行人数据集上的实验表明，V2T-GAN获得的红外模拟图像的结构和纹理特征是正确的，并且在客观指标和主观可视化效果方面优于现有方法。
