Improved Super-Resolution Reconstruction Algorithm Based on SRGAN
Source abstract
Abstract
To improve the performance of image super-resolution reconstruction, this paper optimizes the classical SRGAN model architecture. The original SRResNet is replaced with the EDSR network as the generator, which effectively enhances the ability to restore image details. To address the issue of insufficient multi-scale feature extraction in SRGAN during image reconstruction, an LSK attention mechanism is introduced into the generator. By fusing features from different receptive fields through parallel multi-scale convolution kernels, the model improves its ability to capture key details. To mitigate the instability and overfitting problems in the discriminator training, the Mish activation function is used instead of LeakyReLU to improve gradient flow, and a Dropout layer is introduced to enhance the discriminator’s generalization ability, preventing overfitting to the generator. Additionally, a staged training strategy is employed during adversarial training. Experimental results show that the improved model effectively enhances image reconstruction quality while maintaining low complexity. The generated results exhibit clearer details and more natural visual effects. On the public datasets Set5, Set14, and BSD100, compared to the original SRGAN, the PSNR and SSIM metrics improved by 13.4% and 5.9%, 9.9% and 6.0%, and 6.8% and 5.8%, respectively, significantly enhancing the reconstruction of super-resolution images, achieving more refined and realistic image quality improvement. The model also demonstrates stronger generalization ability on complex cross-domain data, such as remote sensing images and medical images. The improved model achieves higher-quality image reconstruction and more natural visual effects while maintaining moderate computational overhead, validating the effectiveness of the proposed improvements.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image Processing Techniques · Image Processing Techniques and Applications · Advanced Vision and Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Electronic Engineering Department, Tianjin University of Technology and Education, Tianjin 300222, China
Design Department, Kyushu University, Fukuoka 815-8540, Japan
Information Tech & Engineering Department, Tianjin University of Technology and Education, Tianjin 300222, China
Funding
National Natural Science Foundation of China
References (34)
Show source-provided references
1. Medical image super-resolution for smart healthcare applications: A comprehensive survey10.1016/j.inffus.2023.102075 ↗
2. A comprehensive review of deep learning-based single image super-resolution10.7717/peerj-cs.621 ↗
3. Mei, Y., Fan, Y., and Zhou, Y. (2021, January 20–25). Image Super-Resolution with Non-Local Sparse Attention. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Nashville, TN, USA.10.1109/CVPR46437.2021.00352 ↗
4. Image Super-Resolution Using Deep Convolutional Networks10.1109/TPAMI.2015.2439281 ↗
5. Kim, J., Lee, J.K., and Lee, K.M. (2016, January 27–30). Accurate Image Super-Resolution Using Very Deep Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.182 ↗
6. Shi, W., Caballero, J., Huszár, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., and Wang, Z. (2016, January 27–30). Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.207 ↗
7. Transformer-based self-supervised image super-resolution method
8. Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A.P., Tejani, A., Totz, J., and Wang, Z. (2016, January 27–30). Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2017.19 ↗
9. Image Super-Resolution Reconstruction Algorithm Based on Super-Resolution Generative Adversarial Network and Swin Transformer
10. DESRGAN: Detail-enhanced generative adversarial networks for single-image super-resolution
11. Zhang, H., and Liu, J. (2025). Parallel attention recursive generalization transformer for image super-resolution. Sci. Rep., 15.10.1038/s41598-025-92377-y ↗
12. Cao, Y., Deng, K., Li, C., Zhang, X., and Li, Y. (2022). Improving Image Super-Resolution Based on Multiscale Generative Adversarial Networks. Entropy, 24.10.3390/e24081030 ↗
13. Limited Discriminator GAN using Explainable AI Model for Overfitting Problem10.1016/j.icte.2021.12.014 ↗
14. Lim, B., Son, S., Kim, H., Nah, S., and Lee, K.M. (2017, January 21–26). Enhanced Deep Residual Networks for Single Image Super-Resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA.10.1109/CVPRW.2017.151 ↗
15. LSKNet: A Foundation Lightweight Backbone for Remote Sensing10.1007/s11263-024-02247-9 ↗
16. JOA-GAN: An Improved Single-Image Super-Resolution Network for Remote Sensing Based on GAN10.1049/ipr2.13192 ↗
17. The Effect of Leaky ReLUs on the Training and Generalization of Overparameterized Networks
18. Optimizing CNN-BiGRU Performance: Mish Activation and Comparative Analysis with ReLU
19. Liu, Z., Xu, Z., Jin, J., Shen, Z., and Darrell, T. (2023, January 23–29). Dropout Reduces Underfitting. Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, USA.
20. Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution
21. Wang, Y., Li, L., Yang, J., Lin, Z., and Wang, Y. (2023, January 10–16). Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective. Proceedings of the Advances in Neural Information Processing Systems 36 (NeurIPS), New Orleans, LA, USA.
22. Wang, H., Zhang, A., Zheng, S., Shi, X., Li, M., and Wang, Z. (2022, January 17–23). Removing Batch Normalization Boosts Adversarial Training. Proceedings of the 39th International Conference on Machine Learning, PMLR, Baltimore, MD, USA.
23. Chen, H., Hao, J., Zhao, K., Yuan, K., Sun, M., Zhou, C., and Hu, W. (IEEE Trans. Circuits Syst. Video Technol., 2024). CasSR: Activating Image Power for Real-World Image Super-Resolution, IEEE Trans. Circuits Syst. Video Technol., early access.
24. SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolution
25. Bevilacqua, M., Roumy, A., Guillemot, C., and Alberi-Morel, M.L. (2012, January 3–7). Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding. Proceedings of the British Machine Vision Conference (BMVC), Surrey, UK.10.5244/C.26.135 ↗
26. Zeyde, R., Elad, M., and Protter, M. (July, January 28). On Single Image Scale-Up using Sparse-Representations. Proceedings of the International Conference on Curves and Surfaces, Oslo, Norway.
27. Martin, D.R., Fowlkes, C., Tal, D., and Malik, J. (2001, January 7–14). A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics. Proceedings of the International Conference on Computer Vision (ICCV), Vancouver, BC, Canada.
28. Abnar, S., Shah, H., Busbridge, D., Elnouby Ali, A.M., Susskind, J., and Thilak, V. (2025). Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models. arXiv.
29. Yang, Y., and Newsam, S. (2010, January 2–5). Bag-of-Visual-Words and Spatial Extensions for Land-Use Classification. Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM GIS), San Jose, CA, USA.10.1145/1869790.1869829 ↗
30. Hasan, R., Behnoudfar, P., MacKinlay, D., and Poulet, T. (2025, January 11–15). PC-SRGAN: Physically Consistent Super-Resolution Generative Adversarial Network for General Transient Simulations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/TPAMI.2025.3596647 ↗
31. Deep-Learning Methods for Parallel Magnetic Resonance Imaging Reconstruction: A Survey of the Current Approaches, Trends, and Issues10.1109/MSP.2019.2950640 ↗
32. Zhang, L., Wang, H., and Chen, X. (2025, January 23–27). Uncertainty Estimation Using Boundary Prediction for Medical Image Super-Resolution. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Daejeon, Republic of Korea.
33. Liu, Y., and Zhang, T. (IEEE Trans. Pattern Anal. Mach. Intell., 2024). Unleashing the Power of One-Step Diffusion based Image Super-Resolution, IEEE Trans. Pattern Anal. Mach. Intell., early access.
34. Chen, J., and Wu, T. (March, January 25). Stabilized SRGAN with Relativistic Discriminators for Nighttime Light Image Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Philadelphia, PA, USA.