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{170509,
        author = {Bussa Sai Lahari and Vemula Ashwitha and Bhukya Geethika and Cheviti Uday Kumar and Dr. G . Aparna},
        title = {Convolutional Deblurring of Natural Imaging},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {7},
        pages = {1177-1182},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=170509},
        abstract = {Image blur is a common issue in natural photography, caused by factors such as camera shake, defocus, and motion, which degrade the quality of captured images. This project focuses on developing a deep learning- based convolutional neural network (CNN) model to deblur natural images and restore visual quality. The model leverages advanced architectures such as autoencoders or GANs (Generative Adversarial Networks) to perform image deblurring tasks. The approach begins with pre-processing a dataset of blurred and sharp image pairs to train the model to differentiate and correct blurry images. Techniques like convolutional layers and up sampling are employed to extract features and recover fine details. The model is trained and evaluated using a comprehensive dataset, demonstrating its capability to restore high-frequency image content and improve overall sharpness. Results show that the CNN- based deblurring model can significantly enhance image clarity and can be applied to various real-world scenarios such as photography, surveillance, and medical imaging. This work contributes to the broader field of computer vision by providing a robust method for mitigating blur artifacts in natural images.},
        keywords = {Image deblurring, Optical blur, natural, image processing, Convolutional Neural Networks (CNN), Deep Learning, Generative Adversariall Networks (GANS), Image Restoration, Sharpness Recovery, Computer Vision.},
        month = {December},
        }