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{184483,
        author = {Yagati Karunasagar},
        title = {Enhanced Image Dehazing using Attention-based Generative adversarial networks with Perceptual loss},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {1811-1816},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184483},
        abstract = {This paper proposes a hybrid deep learning model for single image dehazing, uniquely combining three distinct components: a CNN-based Generator, a GAN framework with a CNN-based Discriminator, and a VGG19 network used for perceptual loss. The Generator is guided by an attention mechanism to focus on haze-affected regions, while adversarial learning from the Discriminator enhances image realism. The perceptual loss derived from VGG19 further refines image structure and texture similarity. This trio of CNN, GAN, and VGG19 distinguishes the model as hybrid, leveraging the strengths of each to significantly improve dehazing quality and perceptual clarity},
        keywords = {Attention Mechanism, Generative Adversarial Networks (GAN), Hybrid Model, Image Dehazing, Perceptual Loss, VGG19.},
        month = {September},
        }