APE-GAN: A colorization method for focal areas of infrared images guided by an improved attention mask mechanism

• Published in: Computers & graphics Vol. 124; p. 104086
• Main Authors: Ren, Wenchao, Li, Liangfu, Wen, Shiyi, Ai, Lingmei
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.11.2024
• Subjects: Attention mask; Colorizing infrared images; Composite loss; Generative adversarial network; Colorizing infrared images; Composite loss; Attention mask; Generative adversarial network
• ISSN: 0097-8493
• DOI: 10.1016/j.cag.2024.104086

Due to their minimal susceptibility to environmental changes, infrared images are widely applicable across various fields, particularly in the realm of traffic. Nonetheless, a common drawback of infrared images lies in their limited chroma and detail information, posing challenges for clear information retrieval. While extensive research has been conducted on colorizing infrared images in recent years, existing methods primarily focus on overall translation without adequately addressing the foreground area containing crucial details. To address this issue, we propose a novel approach that distinguishes and colors the foreground content with important information and the background content with less significant details separately before fusing them into a colored image. Consequently, we introduce an enhanced generative adversarial network based on Attention mask to meticulously translate the foreground content containing vital information more comprehensively. Furthermore, we have carefully designed a new composite loss function to optimize high-level detail generation and improve image colorization at a finer granularity. Detailed testing on IRVI datasets validates the effectiveness of our proposed method in solving the problem of infrared image coloring. •This paper presents a generator that utilizes an improved attention mask mechanism.•A composite loss function is designed to improve the color effect of infrared image.•The validity of the method was validated using publicly available datasets. [Display omitted]