Enhancement of Low Resolution Natural Images Using Deep Learning Based Super Resolution Techniques

Image super-resolution is an important image processing task that aims to reconstruct a high resolution image from a low resolution input. Conventional interpolation methods often produce blurred edges, loss of texture, and pixelated outputs, particularly when images contain noise, compression artefacts, or complex real world degradations. This work proposes a hybrid CNN Transformer GAN framework for natural image super resolution. The CNN component extracts local features such as edges, patterns, and fine textures; the Transformer component captures long range dependencies and preserves global image structure; and the Generative Adversarial Network (GAN) component improves perceptual quality by generating sharper and more realistic visual details. The proposed model supports 2X, 4X, and 8X upscaling, with 4X selected as the primary evaluation scale because it provides a practical balance between image quality and computational complexity. The system is trained using degraded low-resolution images produced through blur, noise, JPEG compression, and downsampling operations. Performance is evaluated using Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Learned Perceptual Image Patch Similarity (LPIPS), Mean Squared Error (MSE), and visual quality analysis. The hybrid architecture is expected to improve edge sharpness, preserve structural details, reduce visual artefacts, and generate natural looking high-resolution outputs compared with conventional CNN and GAN based approaches. The proposed framework can support applications in photo restoration, mobile imaging, surveillance, e-commerce, digital archives, and web image enhancement.

Image Super-Resolution, Deep Learning, Convolutional Neural Network (CNN), Transformer, Generative Adversarial Network (GAN)

1. Aakerberg, A., Johansen, A. S., Nasrollahi, K., & Moeslund, T. B. (2022). Semantic segmentation guided real-world super-resolution. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW). https://doi.org/10.1109/WACVW54805.2022.00051 [Google Scholar] [Crossref]

2. Xu, X., Wei, P., Chen, W., Liu, Y., Mao, M., Lin, L., & Li, G. (2022). Dual adversarial adaptation for cross-device real-world image super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5657–5666. [Google Scholar] [Crossref]

3. Liu, A., Liu, Y., Gu, J., Qiao, Y., & Dong, C. (2023). Blind image super-resolution: A survey and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5), 5461–5480. [Google Scholar] [Crossref]

4. Wei, P., Xie, Z., Li, G., & Lin, L. (2023). Taylor neural network for real-world image super-resolution. IEEE Transactions on Image Processing. https://doi.org/10.1109/TIP.2023.3255107 [Google Scholar] [Crossref]

5. Zhang, W., Li, X., Shi, G., Chen, X., Qiao, Y., Zhang, X., Wu, X.-M., & Dong, C. (2023). Real-world image super-resolution as multi-task learning. In Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS). [Google Scholar] [Crossref]

6. Wang, X., Liang, Z., Wang, Y., Yang, H., An, W., & Guo, Y. (2022). Real-world light field image super-resolution via degradation modulation. [Google Scholar] [Crossref]

7. Wei, P., Sun, Y., Guo, X., Liu, C., Li, G., Chen, J., Ji, X., & Lin, L. (2023). Towards real-world burst image super-resolution: Benchmark and method. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 13187–13196. [Google Scholar] [Crossref]

8. Chen, X., Wang, X., Zhang, W., Kong, X., Qiao, Y., Zhou, J., & Dong, C. (2023). HAT: Hybrid attention transformer for image restoration. [Google Scholar] [Crossref]

9. Tian, C., Zhang, X., Zhu, Q., Zhang, B., & Lin, J. C.-W. (2022). Generative adversarial networks for image super-resolution: A survey. [Google Scholar] [Crossref]

10. Lin, W. (2022). Single image super-resolution quality assessment: A real-world dataset, subjective studies, and an objective metric. IEEE Transactions on Image Processing, 31, 2279–2294. https://doi.org/10.1109/TIP.2022.3154588 [Google Scholar] [Crossref]

11. Deviyani, S., Hoplamaz, F., & Paul, M. (2022). How real is real: Evaluating the robustness of real-world super-resolution. [Google Scholar] [Crossref]

12. Babaguchi, N., & Aizawa, K. (2022). Robust real-world image super-resolution against adversarial attacks. [Google Scholar] [Crossref]

• Seismic Performance Evaluation of Multi-Storey RCC Buildings with Shear Walls Using ETABS
• Research Trends and Intellectual Structure of Game-Based Learning in Engineering Higher Education: A Bibliometric Analysis
• Jiadhal River, Assam, India: An integrated Remote Sensing and GIS approach to study the sorrow of Dhemaji
• Smart Food Recommendation System Based on Age, Mood and Weather
• Environmental Justice and Inequality in Municipal Solid Waste Service Delivery in Owerri Municipality, Nigeria