IR2VI: Enhanced Night Environmental Perception by Unsupervised Thermal Image Translation
This addresses night vision enhancement for applications in dark environments without artificial lighting, representing an incremental improvement over existing GAN-based methods.
The paper tackles the problem of enhancing night vision by developing an unsupervised thermal-to-visible image translation framework called IR2VI, which uses GANs with a structure connection module and ROI focal loss to improve mapping and detail, showing superiority over baseline methods.
Context enhancement is critical for night vision (NV) applications, especially for the dark night situation without any artificial lights. In this paper, we present the infrared-to-visual (IR2VI) algorithm, a novel unsupervised thermal-to-visible image translation framework based on generative adversarial networks (GANs). IR2VI is able to learn the intrinsic characteristics from VI images and integrate them into IR images. Since the existing unsupervised GAN-based image translation approaches face several challenges, such as incorrect mapping and lack of fine details, we propose a structure connection module and a region-of-interest (ROI) focal loss method to address the current limitations. Experimental results show the superiority of the IR2VI algorithm over baseline methods.