Image Super-Resolution Reconstruction Algorithm Based on SRGAN and Swin Transformer
Abstract
:1. Introduction
2. Related Work
3. Image Reconstruction Algorithm Combining HO-SRGAN and SWIN Transformer
3.1. Construction of an Improved SRGAN Model
3.2. Design of ISR Reconstruction Algorithm Combining HO-SRGAN and SWIN Tansformer
4. Analysis of Benchmark Performance and Application Effectiveness of HO-SRGAN-ST Model
4.1. Ablation Testing and Benchmark Performance Testing
4.2. Analysis of Model Application Effectiveness
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Yu, M.; Shi, J.; Xue, C.; Hao, X.; Yan, G. A review of single image super-resolution reconstruction based on deep learning. Multimed. Tools Appl. 2024, 83, 55921–55962. [Google Scholar] [CrossRef]
- Wang, Y.; Li, X.; Nan, F.; Liu, F.; Li, H.; Wang, H.; Qian, Y. Image super-resolution reconstruction based on generative adversarial network model with feedback and attention mechanisms. Multimed. Tools Appl. 2022, 81, 6633–6652. [Google Scholar] [CrossRef]
- Tao, P.; Yang, D. RSC-WSRGAN super-resolution reconstruction based on improved generative adversarial network. Signal Image Video Process. 2024, 18, 7833–7845. [Google Scholar] [CrossRef]
- Li, X.; Dong, W.; Wu, J.; Li, L.; Shi, G. Superresolution image reconstruction: Selective milestones and open problems. IEEE Signal Process. Mag. 2023, 40, 54–66. [Google Scholar] [CrossRef]
- Hu, Y.; Shang, Q. Performance enhancement of BOTDA based on the image super-resolution reconstruction. IEEE Sens. J. 2021, 22, 3397–3404. [Google Scholar] [CrossRef]
- Sharma, A.; Shrivastava, B.P. Different techniques of image SR using deep learning: A review. IEEE Sens. J. 2022, 23, 1724–1733. [Google Scholar] [CrossRef]
- Daihong, J.; Sai, Z.; Lei, D.; Yueming, D. Multi-scale generative adversarial network for image super-resolution. Soft Comput. 2022, 26, 3631–3641. [Google Scholar] [CrossRef]
- Lei, H.; Wang, Z.; Tian, C.; Zhang, Y. An improved SRGAN infrared image super-resolution reconstruction algorithm. J. Syst. Simul. 2021, 33, 2109–2118. [Google Scholar] [CrossRef]
- Abi-Rizk, R.; Orieux, F.; Abergel, A. Super-Resolution Hyperspectral Reconstruction with Majorization-Minimization Algorithm and Low-Rank Approximation. IEEE Trans. Comput. Imaging 2022, 8, 260–272. [Google Scholar] [CrossRef]
- Ahmadi, S.; Kästner, L.; Hauffen, J.C.; Jung, P.; Ziegler, M. Photothermal-SR-Net: A Customized Deep Unfolding Neural Network for Photothermal Super Resolution Imaging. IEEE Trans. Instrum. Meas. 2022, 71, 1–9. [Google Scholar] [CrossRef]
- Esmaeilzehi, A.; Ahmad, M.O.; Swamy, M.N.S. SRNMSM: A Deep Light-Weight Image Super Resolution Network Using Multi-Scale Spatial and Morphological Feature Generating Residual Blocks. IEEE Trans. Broadcast. 2022, 68, 58–68. [Google Scholar] [CrossRef]
- Mishra, D.; Hadar, O. CLSR: Contrastive Learning for Semi-Supervised Remote Sensing Image Super-Resolution. IEEE Geosci. Remote Sens. Lett. 2023, 20, 1–5. [Google Scholar] [CrossRef]
- Chen, X.; Zhao, H. A novel fast reconstruction method for single image super resolution task. Neural Process. Lett. 2023, 55, 9995–10010. [Google Scholar] [CrossRef]
- Fu, L.; Jiang, H.; Wu, H.; Yan, S.; Wang, J.; Wang, D. Image super-resolution reconstruction based on instance spatial feature modulation and feedback mechanism. Appl. Intell. 2023, 53, 601–615. [Google Scholar] [CrossRef]
- Khmag, A. Natural digital image mixed noise removal using regularization Perona–Malik model and pulse coupled neural networks. Soft Comput. 2023, 27, 15523–15532. [Google Scholar] [CrossRef]
- Khmag, A. Additive Gaussian noise removal based on generative adversarial network model and semi-soft thresholding approach. Multimed. Tools Appl. 2023, 82, 7757–7777. [Google Scholar] [CrossRef]
- Chen, Y.; Xia, R.; Yang, K.; Zou, K. MFFN: Image super-resolution via multi-level features fusion network. Vis. Comput. 2024, 40, 489–504. [Google Scholar] [CrossRef]
- Kshem, W.; Khmag, A. Improving Block Matching and 3 Dimensions (BM3D) Filtering for Image Noise Removal Using Discrete Wavelet Transformation (DWT). In Proceedings of the 2024 IEEE 4th International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA), Tripoli, Libya, 19–21 May 2024; pp. 375–380. [Google Scholar] [CrossRef]
- Guo, J.; Lv, F.; Shen, J.; Liu, J.; Wang, M. An improved generative adversarial network for remote sensing image super-resolution. IET Image Process. 2023, 17, 1852–1863. [Google Scholar] [CrossRef]
- Abbas, R.; Gu, N. Improving deep learning-based image super-resolution with residual learning and perceptual loss using SRGAN model. Soft Comput. 2023, 27, 16041–16057. [Google Scholar] [CrossRef]
- Ma, C.; Rao, Y.; Lu, J.; Zhou, J. Structure-preserving image super-resolution. IEEE Trans. Pattern Anal. Mach. Intell. 2021, 44, 7898–7911. [Google Scholar] [CrossRef]
- Huang, S.; Liu, X.; Tan, T.; Hu, M.; Wei, X.; Chen, T.; Sheng, B. TransMRSR: Transformer-based self-distilled generative prior for brain MRI super-resolution. Vis. Comput. 2023, 39, 3647–3659. [Google Scholar] [CrossRef]
- Guo, X.; Tu, Z.; Zhang, H.; Dong, H. Super-resolution reconstruction based on generative adversarial networks with dual branch half instance normalization. IET Image Process. 2024, 18, 1434–1446. [Google Scholar] [CrossRef]
- Hou, Y.; Canul-Ku, M.; Cui, X.; Zhu, M. Super-resolution reconstruction of vertebrate microfossil computed tomography images based on deep learning. X-Ray Spectrom. 2024, 53, 405–414. [Google Scholar] [CrossRef]
- Liu, X.; Su, S.; Gu, W.; Yao, T.; Shen, J.; Mo, Y. Super-resolution reconstruction of CT images based on multi-scale information fused generative adversarial networks. Ann. Biomed. Eng. 2024, 52, 57–70. [Google Scholar] [CrossRef]
- Wang, G.; Wang, K.C.; Yang, G. Reconstruction of sub-mm 3D pavement images using recursive generative adversarial network for faster texture measurement. Comput. Aided Civ. Infrastruct. Eng. 2023, 38, 2206–2224. [Google Scholar] [CrossRef]
- Hu, Y.; Li, J.; Huang, Y.; Gao, X. Image super-resolution with self-similarity prior guided network and sample-discriminating learning. IEEE Trans. Circuits Syst. Video Technol. 2021, 32, 1966–1985. [Google Scholar] [CrossRef]
- Zhang, T.; Hu, G.; Yang, Y.; Du, Y. A super-resolution reconstruction method for shale based on generative adversarial network. Transp. Porous Media 2023, 150, 383–426. [Google Scholar] [CrossRef]
- Liu, H.; Shao, M.; Wang, C.; Cao, F. Image super-resolution using a simple transformer without pretraining. Neural Process. Lett. 2023, 55, 1479–1497. [Google Scholar] [CrossRef]
- Ju, R.Y.; Chen, C.C.; Chiang, J.S.; Lin, Y.S.; Chen, W.H. Resolution enhancement processing on low quality images using swin transformer based on interval dense connection strategy. Multimed. Tools Appl. 2024, 83, 14839–14855. [Google Scholar] [CrossRef]
- Wang, J.; Zou, Y.; Alfarraj, O.; Sharma, P.K.; Said, W.; Wang, J. Image super-resolution method based on the interactive fusion of transformer and CNN features. Vis. Comput. 2024, 40, 5827–5839. [Google Scholar] [CrossRef]
- Gao, X.; Wu, S.; Zhou, Y.; Wu, X.; Wang, F.; Hu, X. Lightweight image super-resolution via multi-branch aware CNN and efficient transformer. Neural Comput. Appl. 2024, 36, 5285–5303. [Google Scholar] [CrossRef]
- Bhosle, K.; Musande, V. Evaluation of deep learning CNN model for recognition of devanagari digit. Artif. Intell. Appl. 2023, 1, 114–118. [Google Scholar] [CrossRef]
Component | Details |
---|---|
CPU | Intel® Core™ i9-10900K CPU @ 3.70 GHz × 32 |
GPU | NVIDIA GeForce RTX 3080 |
RAM | 64 GB DDR4 |
Storage | 1 TB NVMe SSD |
Operating System | Ubuntu 20.04 LTS |
Framework | PyTorch |
Python Version | Python 3.8 |
CUDA Version | CUDA 11.1 |
cuDNN Version | cuDNN 8.0 |
Learning Rate | 0.0001 |
Weight Decay | 0.001 |
Training Data Ratio | 80% |
Testing Data Ratio | 20% |
Model Configuration | Set5-PSNR (dB) | Set5-SSIM | Urban100-PSNR (dB) | Urban100-SSIM | Reconstruction Time (s) |
---|---|---|---|---|---|
Remove Swin Transformer (HO-SRGAN) | 31.85 | 0.89 | 26.43 | 0.81 | 0.08 |
Remove SRGAN (HO-ST) | 32.47 | 0.91 | 27.52 | 0.84 | 0.06 |
Remove Perceptual Loss | 33.12 | 0.92 | 28.04 | 0.86 | 0.07 |
Full Model (HO-SRGAN-ST) | 34.23 | 0.94 | 29.58 | 0.89 | 0.08 |
Index | SRGAN | EDSR | RCAN | HO-SRGAN-ST |
---|---|---|---|---|
Precision | 0.85 | 0.88 | 0.90 | 0.96 |
Recall | 0.83 | 0.087 | 0.89 | 0.98 |
F1 | 0.84 | 0.87 | 0.90 | 0.97 |
Reconstruction error | 0.045 | 0.038 | 0.029 | 0.011 |
Reconstruction time for each image/s | 0.16 | 0.12 | 0.08 | 0.02 |
Action Classification | Reconstruction | SRGAN | EDSR | RCAN | HO-SRGAN-ST |
---|---|---|---|---|---|
Natural landscape images | Accuracy rate/% | 89.54 | 91.25 | 94.68 | 97.58 |
PSNR/dB | 29.25 | 32.80 | 34.64 | 40.03 | |
Urban building images | Accuracy rate/% | 88.72 | 90.09 | 93.43 | 96.95 |
PSNR/dB | 31.27 | 32.97 | 36.77 | 41.57 | |
Complex texture images | Accuracy rate/% | 90.15 | 92.47 | 94.22 | 97.21 |
PSNR/dB | 29.79 | 31.15 | 35.55 | 39.85 | |
Portrait images | Accuracy rate/% | 90.23 | 91.78 | 94.06 | 98.03 |
PSNR/dB | 28.64 | 32.01 | 34.40 | 42.62 |
Method | PSNR (dB) | SSIM | Reconstruction Time (s) | Mean Absolute Error (MAE) | High-Frequency Detail Recovery Rate (HFDR, %) |
---|---|---|---|---|---|
MM-LRHSR | 25.45 | 0.80 | 0.10 | 0.1267 | 85.2 |
RD-SRGAN | 27.10 | 0.83 | 0.09 | 0.1145 | 88.7 |
CL-SSR | 26.85 | 0.82 | 0.08 | 0.1189 | 87.5 |
EA-GAN | 28.34 | 0.85 | 0.07 | 0.1094 | 90.3 |
HO-SRGAN-ST | 29.58 | 0.89 | 0.08 | 0.0978 | 92.8 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Sun, C.; Wang, C.; He, C. Image Super-Resolution Reconstruction Algorithm Based on SRGAN and Swin Transformer. Symmetry 2025, 17, 337. https://doi.org/10.3390/sym17030337
Sun C, Wang C, He C. Image Super-Resolution Reconstruction Algorithm Based on SRGAN and Swin Transformer. Symmetry. 2025; 17(3):337. https://doi.org/10.3390/sym17030337
Chicago/Turabian StyleSun, Chuilian, Chunmeng Wang, and Chen He. 2025. "Image Super-Resolution Reconstruction Algorithm Based on SRGAN and Swin Transformer" Symmetry 17, no. 3: 337. https://doi.org/10.3390/sym17030337
APA StyleSun, C., Wang, C., & He, C. (2025). Image Super-Resolution Reconstruction Algorithm Based on SRGAN and Swin Transformer. Symmetry, 17(3), 337. https://doi.org/10.3390/sym17030337