Copyright © 2026 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{180430,
        author = {Ms. Kimaya Churi},
        title = {Advances in Deep Learning for Automatic Image Colorization: A Survey},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {2834-2836},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180430},
        abstract = {Automatic image colorization is a vital challenge in the field of computer vision that involves generating plausible colour images from grayscale input. This task has extensive applications in areas such as historical image restoration, digital media production, and content creation. Traditional approaches to this task involved manual work or relied on rule-based algorithms. However, with the emergence of deep learning techniques, particularly Conditional Generative Adversarial Networks (cGANs), the quality and realism of colorized images have dramatically improved. This survey explores the current state-of-the-art approaches in automatic image colorization, compares various techniques, and evaluates their performance using standard metrics such as PSNR, SSIM, and FID. Our findings reveal that cGAN-based models outperform traditional and CNN-based methods in generating perceptually realistic results.},
        keywords = {},
        month = {June},
        }