Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{161885,
        author = {Aayushi Pandey and Abhay Singh Rana},
        title = {Coloring of Grayscale Images using Generative Adversarial Network},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {10},
        number = {6},
        pages = {493-501},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=161885},
        abstract = {Attempts to colorize grayscale photographs into natural-looking colorful images have been made in the past. The concept of automatic image colorization has piqued attention in the recent decade for a variety of applications, including the restoration of aged or deteriorated photos. There have been various time and energy consuming traditional approaches. Throughout all the research, various deep learning approaches have evolved as a development in the world of technology. The most important reason to colorize a picture is to give it a unique and genuine appearance. In this research, we compare how colorization was handled previously to how deep learning is tackling it now. Many attempts are made linear to get the simplest objectives. In this research, we compare how colorization was handled previously to how deep learning is tackling it now. Many attempts are made in the linear manner to achieve the simplest results, which range from choosing colors from one end to the other, deciding the color palette, and a variety of other metrics. Deep learning user-guided and non-guided approaches have been established as technology has advanced over the last 20 years. This document compares and contrasts all the methods, as well as their benefits and drawbacks. We're working on an image colorization technique that's completely automated. In this work, we compare how colorization was handled previously to how it is being handled by deep learning. To achieve the best results, many efforts have been made in the linear way, which ranges from selecting colors from one end to the other, deciding the color palette and many other such metrics. With the evolution of technology over these 20 years, deep learning user-guided and non-guided methods have been introduced.},
        keywords = {CIELAB color space, CNN, Colorization, Deep learning, neural network},
        month = {},
        }