International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 1, pp. 241-247, January 2026.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Gangapalli Soniya
Edamadaka Uday Kiran
Shaik Gowsiya
Gundrasam Saketh Ram
Dasari Prasanth Kumar
Department of CSE, Siddartha Institute of Science and Technology, Puttur, India.
Abstract: Noise, blur, and compression artifacts commonly degrade high-resolution images, reducing visual quality and affecting various downstream applications in medical imaging, satellite imaging, and photography. However, traditional image restoration methods usually suffer from balancing accuracy and computational efficiency, and most of them cannot handle large-size high-resolution images. This paper presents an efficient transformer-based model for high-resolution image restoration, termed RestoraNet. Benefiting from the self-attention mechanism, RestoraNet effectively leverages the long-range dependencies and complex contextual information of images, leading to superior restoration performance. In this work, multiscale feature extraction, residual connections, and efficient attention modules will be incorporated into the model for enhancing detail preservation while reducing computational cost.
Keywords: Image Restoration, Transformers, Degradation, High Resolution Images, Satellite Images.
References:
- H. Wu, J. Zheng, C. He, H. Xiao, and S. Luo, “Terahertz image super-resolution restoration using a hybrid-Transformer-based generative adversarial network,” Optics and Lasers in Engineering, vol. 189, p. 108931, Mar. 2025, doi: 10.1016/j.optlaseng.2025.108931.
- S. Yue, Z. Chen, and F. Yin, “Blind compressed image diffusion restoration based on content prior and dense residual connection driven transformer,” Journal of Visual Communication and Image Representation, vol. 115, p. 104674, Dec. 2025, doi: 10.1016/j.jvcir.2025.104674.
- Kuruma Purnima and C. Siva Kumar, “CSUID – Comprehensive synthetic underwater image dataset,” Data in Brief, vol. 55, p. 110723, Jul. 2024, doi: 1016/j.dib.2024.110723
- Y. Guo, C. Tian, J. Liu, C. Di, and K. Ning, “HADT: Image super-resolution restoration using Hybrid Attention-Dense Connected Transformer Networks,” Neurocomputing, vol. 614, p. 128790, Oct. 2024, doi: 10.1016/j.neucom.2024.128790.
- W. Dou et al., “Integrating RGB image with transformer for coded aperture snapshot spectral imaging restoration,” Optics Communications, vol. 583, p. 131642, Feb. 2025, doi: 10.1016/j.optcom.2025.131642.
- Kuruma Purnima and C. Siva Kumar, “Devising a comprehensive synthetic underwater image dataset,” Journal of Visual Communication and Image Representation, p. 104386, Dec. 2024, doi: 1016/j.jvcir.2024.104386.
- Z. Li et al., “Image inpainting based on CNN-Transformer framework via structure and texture restoration,” Applied Soft Computing, vol. 170, p. 112671, Jan. 2025, doi: 10.1016/j.asoc.2024.112671.
- Y. Sun, P. Shi, T. Chen, D. Qi, and K. Xu, “MFET: Multi-frequency enhancement transformer for single-image super-resolution,” Image and Vision Computing, vol. 163, p. 105751, Sep. 2025, doi: 10.1016/j.imavis.2025.105751.
- Jaya Krishna Sunkara, Kuruma Purnima, Suresh Muchakala, Ravisankariah Y, “Super-Resolution Based Image Reconstruction,” International Journal of Computer Science and Technology, vol.2, issue 3, September 2011.
- Q. Wang, Z. Li, S. Zhang, N. Chi, and Q. Dai, “A versatile Wavelet-Enhanced CNN-Transformer for improved fluorescence microscopy image restoration,” Neural Networks, vol. 170, pp. 227–241, Nov. 2023, doi: 10.1016/j.neunet.2023.11.039.
- C. Tsai, P.-J. Lee, S. Bergies, J. Liobe, and V. Barzdėnas, “Enhancing satellite image quality with the edge-based wavelet transformer for super-resolution,” Applied Computing and Geosciences, vol. 28, p. 100302, Oct. 2025, doi: 10.1016/j.acags.2025.100302.
- A Hazarathaiah, Dharani Udayabhanu, Anukupalli Anjali, Biruduraju Nymisha, Borra Prathyusha, “An Optimum Deraining Scheme using Sparse Coding,” International Journal of Emerging Research in Engineering, Science, and Management, vol. 1, no. 2, pp. 7-11, 2022. doi: 10.58482/ijeresm.v1i2.2.