In many real world scenarios, it is difficult to capture the images in the visible light spectrum (VIS) due to bad lighting conditions. However, the images can be captured in such scenarios using Near-Infrared (NIR) and Thermal (THM) cameras. The NIR and THM images contain the limited details. Thus, there is a need to transform the images from THM/NIR to VIS for better understanding. However, it is non-trivial task due to the large domain discrepancies and lack of abundant datasets. Nowadays, Generative Adversarial Network (GAN) is able to transform the images from one domain to another domain. Most of the available GAN based methods use the combination of the adversarial and the pixel-wise losses (like L1 or L2) as the objective function for training. The quality of transformed images in case of THM/NIR to VIS transformation is still not up to the mark using such objective function. Thus, better objective functions are needed to improve the quality, fine details and realism of the transformed images. A new model for THM/NIR to VIS image transformation called Perceptual Cyclic-Synthesized Generative Adversarial Network (PCSGAN) is introduced to address these issues. The PCSGAN uses the combination of the perceptual (i.e., feature based) losses along with the pixel-wise and the adversarial losses. Both the quantitative and qualitative measures are used to judge the performance of the PCSGAN model over the WHU-IIP face and the RGB-NIR scene datasets. The proposed PCSGAN outperforms the state-of-the-art image transformation models, including Pix2pix, DualGAN, CycleGAN, PS2GAN, and PAN in terms of the SSIM, MSE, PSNR and LPIPS evaluation measures. The code is available at: \url{this https URL}.

中文翻译：

---

PCSGAN：用于热和 NIR 到可见光图像转换的感知循环合成生成对抗网络

在许多现实场景中，由于光照条件不佳，很难捕捉可见光谱 (VIS) 中的图像。但是，可以使用近红外 (NIR) 和热 (THM) 相机在此类场景中捕获图像。NIR 和 THM 图像包含有限的细节。因此，需要将图像从 THM/NIR 转换为 VIS 以便更好地理解。然而，由于领域差异大和缺乏丰富的数据集，这是一项重要的任务。如今，生成对抗网络（GAN）能够将图像从一个域转换到另一个域。大多数可用的基于 GAN 的方法使用对抗性和像素级损失（如 L1 或 L2）的组合作为训练的目标函数。在 THM/NIR 到 VIS 转换的情况下，转换图像的质量仍然达不到使用这种目标函数的标准。因此，需要更好的目标函数来提高转换图像的质量、细节和真实感。引入了一种称为感知循环合成生成对抗网络 (PCSGAN) 的 THM/NIR 到 VIS 图像转换的新模型来解决这些问题。PCSGAN 使用感知（即基于特征的）损失以及像素和对抗性损失的组合。定量和定性测量都用于判断 PCSGAN 模型在 WHU-IIP 人脸和 RGB-NIR 场景数据集上的性能。提出的 PCSGAN 优于最先进的图像转换模型，包括 Pix2pix、DualGAN、CycleGAN、PS2GAN、和 PAN 在 SSIM、MSE、PSNR 和 LPIPS 评估措施方面。代码位于：\url{this https URL}。