Litcius/Paper detail

Innovative Image Enhancement via GANs: Addressing Noise, Resolution, and Artifact Challenges

Abdul Wahab Paracha, Syed Fasih Ali Kazmi, Muhammad Abbas, Haris Anjum, Raja Hashim Ali

202515 citationsDOIOpen Access PDF

Abstract

Generative adversarial networks (GANs) are increasingly used for image enhancement tasks like denoising, super-resolution, and artifact removal. In this study, we propose a robust GAN-based architecture featuring a U-Net-style generator and DCNN-based discriminator, optimized for real-time enhancement. Key contributions include multi-task image refinement using residual and attention modules. Our method is tested on paired datasets comprising low-light medical and artificially degraded images. Results show significant improvements in visual clarity, reduced noise, and improved resolution compared to traditional methods. Evaluation metrics such as inception score (IS) and Fréchet inception distance (FID) confirm the system’s performance. The optimal learning rate (0.0008) was empirically selected for training stability. These results validate the proposed GAN’s efficiency for practical deployment in domains requiring high-quality imaging.

Topics & Concepts

Artifact (error)Computer scienceNoise (video)Resolution (logic)Image (mathematics)Computer visionImage resolutionArtificial intelligenceImage Enhancement TechniquesImage and Signal Denoising MethodsImage Processing Techniques and Applications