Nighttime Thermal Infrared Image Colorization with Feedback-based Object Appearance Learning

1 code implementation • 24 Oct 2023 • Fu-Ya Luo, Shu-Lin Liu, Yi-Jun Cao, Kai-Fu Yang, Chang-Yong Xie, Yong liu, Yong-Jie Li

Extensive experiments illustrate that the proposed FoalGAN is not only effective for appearance learning of small objects, but also outperforms other image translation methods in terms of semantic preservation and edge consistency for the NTIR2DC task.

Colorization Generative Adversarial Network +2