Lightweight Transformer-Fourier Fusion Framework for Efficient Image Super-Resolution
DOI:
https://doi.org/10.37547/ibast/Volume06Issue08-02Keywords:
Image Super-Resolution, Lightweight Architecture, Transformer Networks, Fourier ConvolutionAbstract
Image super-resolution (ISR) has emerged as a critical computer vision task aimed at reconstructing high-resolution visual information from low-resolution inputs. Although deep learning-based approaches have significantly improved reconstruction quality, many existing architectures suffer from high computational complexity, excessive parameter requirements, and limited efficiency in real-time deployment scenarios. This research presents a Lightweight Transformer-Fourier Fusion Framework for Efficient Image Super-Resolution, designed to integrate the long-range dependency modeling capability of transformers with the frequency-domain representation advantages of Fourier-based feature processing. The proposed framework is theoretically positioned around efficient feature extraction, adaptive attention learning, and frequency-aware reconstruction. Transformer-based modules enhance spatial relationship modeling, while Fourier convolution mechanisms improve the preservation of high-frequency image details with reduced computational overhead. The methodology combines lightweight residual feature refinement, transformer-driven contextual enhancement, and frequency-domain fusion to achieve an optimized balance between reconstruction accuracy and computational efficiency. The study analyzes the limitations of conventional convolutional, generative, and attention-based super-resolution approaches and establishes the importance of hybrid architectures for next-generation ISR systems. The proposed framework provides a scalable solution for applications requiring efficient image enhancement, including mobile imaging, medical visualization, remote sensing, and intelligent surveillance systems.
Downloads
References
1. Dabov, K., Foi, A., Katkovnik, V., & Egiazarian, K. (2007).Image denoising by sparse 3-D transform-domain collaborativefiltering.IEEE Transactions on Image Processing,16(8),2080–2095.
2. Gu, S., Sang, N., & Ma, F. (2012). Fast image super resolutionvia local regression. InProceedings of the 21st InternationalConference on Pattern Recognition, 3128–3131.
3. Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., & Wang, Y. (2021).Transformer in transformer. In35th Conference on NeuralInformation Processing Systems.
4. Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A.,Acosta, A.,:::, & Shi, W. (2017). Photo-realistic single imagesuper-resolution using a generative adversarial network. InProceedings of the IEEE Conference on Computer Visionand Pattern Recognition, 4681–4690.
5. Li, Z., Yang, J., Liu, Z., Yang, X., Jeon, G., & Wu, W. (2019).Feedback network for image super-resolution. InProceedingsof the IEEE/CVF Conference on Computer Vision and PatternRecognition, 3867–3876.
6. Lim, B., Son, S., Kim, H., Nah, S., & Mu Lee, K. (2017). Enhanceddeep residual networks for single image super-resolution. InProceedings of the IEEE Conference on Computer Vision andPattern Recognition Workshops,136–144.
7. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L.,Gomez, A. N.,:::, & Polosukhin, I. (2017). Attention is all youneed. In31st Conference on Neural Information ProcessingSystems.
8. Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C.,:::,&Change Loy, C. (2018). ESRGAN: Enhanced super-resolution generative adversarial networks. InProceedingsof the European Conference on Computer VisionWorkshops.
9. Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., & Fu, Y. (2018).Image super-resolution using very deep residual channelattention networks. InProceedings of the EuropeanConference on Computer Vision, 286–301.
10. Ramamurthy, K., Gumber, S., Abdelfattah, W.M. et al. Human AI trust modeling in cognitive systems via ensemble learning and advanced feature engineering. Discov Artif Intell 6, 366 (2026). https://doi.org/10.1007/s44163-026-01255-7
11. Philip, P. G. (2026). Artificial Intelligence–Driven Intelligent Project Management: an integrated framework for planning, scheduling and control in engineering and construction projects. Journal of Engineering and Artificial Intelligence, 02(02), 01–09. https://doi.org/10.64142/jeai.2.2.50
12. Chowdhury, W. A. (2025). Blockchain for Sustainable Supply Chain Management: Reducing Waste Through Transparent Resource Tracking. Journal of Procurement and Supply Chain Management, 4(2), 28–34. https://doi.org/10.58425/jpscm.v4i2.435
13. S. R. Lankala, M. R. Marri, A. Jain, G. G. Battu, U. Lakhina and S. Singla, "Optimal Financial Fraud Detection and Alerting Mechanism in Cloud Computing Using Deep Belief Network," 2025 International Conference on Emerging Trends in Networks and Computer Communications (ETNCC), Windhoek, Namibia, 2025, pp. 743-748, doi: 10.1109/ETNCC66224.2025.11299665.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Dr. Chinedu Okafor
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in this journal are licensed under the Creative Commons Attribution 4.0 International License (CC-BY 4.0). Under this license:
- Share: Copy and redistribute the material in any medium or format
- Adapt: Remix, transform, and build upon the material for any purpose, including commercially
Attribution required: You must give appropriate credit, provide a link to the license, and indicate if changes were made.
License URL: https://creativecommons.org/licenses/by/4.0/
Authors retain copyright of their work while granting the journal first publication rights.
