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{171706,
        author = {S Prasanna Lakshmi and D Manaswini and K Nikshipta and V Rishik and DR M Rajeshwar},
        title = {Adversarial Network Papers},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {8},
        pages = {863-867},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=171706},
        abstract = {Critical information about images becomes lost because deblurring with motion blur, defocus blur, or camera shake degrades such images and that's problematic in a multitude of applications. In this paper, an effort has been made toward a more efficient approach by using the recently designed deep learning technique Generative Adversarial Networks to achieve the design of an image deblurring system. It would transform the blurred images to become sharper clear versions through adversarial interaction of a Generator and a Discriminator trained on paired images of the GoPro dataset - images blurred and their sharp version counterparts. This system combines adversarial, content, and perceptual loss to ensure visually and structurally accurate outputs. Performance in PSNR and SSIM signifies the effectiveness of the system in producing high resolution images with sharpness. Implemented using Python deep learning frameworks: TensorFlow and Keras, libraries include OpenCV for preprocessing and visualization tools for evaluating the output. This deblurring model shows tremendous potential to applications that demand clearer images of increased quality, such as the restoration of documents, in medical imaging, and digital archiving.},
        keywords = {},
        month = {January},
        }