@inproceedings{f34e06e4033248b2b86aa705d6a8f31f,
title = "An Unsupervised Colorization Method of Thermal Infrared Image Based on Edge Consistency",
abstract = "Due to the lack of pixel level structural matching data, thermal infrared grayscale images are more difficult to color than visible and near-infrared grayscale images. Therefore, this paper proposes a unsupervised learning method based on CycleGAN. On the basis of CycleGAN, a pre trained edge monitor is introduced to calculate the edge feature map before and after image transformation, and the edge similarity loss function is calculated as the basis for optimizing the neural network parameters. The experimental results show that the proposed method effectively reduces the loss of effective edge information during the coloring process and suppresses the generation of abnormal edge information during the coloring process.",
keywords = "Thermal to visible, deep learning, edge consistency loss, style transfer",
author = "Jiaming Cai and Xin Tang and Yao Hu and Shaohui Zhang",
note = "Publisher Copyright: {\textcopyright} 2023 SPIE.; 3rd International Conference on Advanced Algorithms and Neural Networks, AANN 2023 ; Conference date: 05-05-2023 Through 07-05-2023",
year = "2023",
doi = "10.1117/12.3004945",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Pavel Loskot and Xiaofeng Ding",
booktitle = "Third International Conference on Advanced Algorithms and Neural Networks, AANN 2023",
address = "United States",
}