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{188998,
        author = {Manish S Nandi and Sakshi and Sharanabasappa and Prof. Rajashekhar},
        title = {Image Resolution Enhancement Using GAN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {4284-4289},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188998},
        abstract = {High-resolution image generation and enhancement are critical requirements in various domains, including medical imaging, surveillance, and satellite photography. Traditional generative models and interpolation techniques, such as bilinear and bicubic scaling, often fail to produce high-quality results, leading to blurry outputs that lack high-frequency details and realistic textures. This paper presents a system for Image Resolution Enhancement Using Generative Adversarial Networks (GANs). The proposed methodology leverages the adversarial dynamics between two neural networks: a Generator, which creates synthetic data from random noise, and a Discriminator, which distinguishes between real and generated samples.
Unlike standard Convolutional Neural Networks (CNNs) that may struggle with texture preservation, the GAN architecture allows the system to learn complex real-world data distributions directly from the dataset without heavy manual feature engineering. The training process utilizes loss functions such as Binary Cross Entropy to optimize the adversarial competition, resulting in the generation of highly realistic and sharp synthetic images. This study analyzes the mechanism of GANs, evaluates their performance against existing generative approaches, and demonstrates their effectiveness in applications such as image restoration and super-resolution.},
        keywords = {Generative Adversarial Networks (GAN), Image Super-Resolution, Deep Learning, Generator, Discriminator, Image Enhancement.},
        month = {December},
        }