Revolutionizing Thermal Imaging: GAN-Based Vision Transformers for Image Enhancement

In this paper, we propose a new architecture for thermal image enhancement in which we exploit the strengths of both architecture-based vision transformers and generative adversarial networks. Our approach includes the introduction of a thermal loss function, which is specifically employed to produce high quality images. In addition, we consider fine-tuning based on visible images for thermal image restoration, resulting in an overall improvement in image quality. The performance of our proposed architecture is evaluated using visual quality metrics. The results show significant improvements over the original thermal images and over other established enhancement methods on a subset of the KAIST dataset. The performance of the proposed enhancement architecture is also verified on the detection results by obtaining better performance with a considerable margin considering different versions of the YOLO detector.