← Back to Volume 5

Optimization of Super-Resolution Features via Deep Learning Techniques

Yongkang Hu, Chuyue Jing, Ziyuan Li, Xiao Liu
pp.493-501 DOI: 10.62051/k87ej039 August 12, 2024
Download PDF
Abstract: This manuscript delves into the pivotal role of feature optimization within the realm of deep learning-driven super-resolution techniques, a topic of considerable importance across diverse domains such as medical imaging and electron microscopy. The paper confronts the inherent challenges posed by deep learning in super-resolution tasks, including issues related to complexity, computational burden, and the paucity of model generalizability. It underscores the significance of feature optimization strategies, particularly the application of time-to-frequency transformation techniques such as wavelet and Fourier transforms, as well as attention mechanisms, in enhancing model efficiency and curtailing the demand on computational resources. A central theme of the discourse is the efficacy of amalgamating time-frequency separation methods — notably wavelet and Fourier transforms — with attention mechanisms in super-resolution endeavors. This integrated approach, termed multi-scale feature fusion, is lauded for its capacity to augment the model's attentiveness to high-frequency details, which are crucial in super-resolution. This fusion strategy not only optimizes the allocation of computational resources but also elevates learning performance.
Keywords: Super-Resolution, deep learning, feature optimization, time-to-frequency transformation, wavelet transform.
APA Citation: Yongkang Hu, Chuyue Jing, Ziyuan Li, Xiao Liu (2024). Optimization of Super-Resolution Features via Deep Learning Techniques. Transactions on Computer Science and Intelligent Systems Research, 5(1), 493-501. https://doi.org/10.62051/k87ej039

References

  1. Umirzakova, S., Ahmad, S., Khan, L. U., & Whangbo, T. (2024). Medical image super-resolution for smart healthcare applications: A comprehensive survey. Information Fusion, 103.
  2. (2023). Medical image super-resolution reconstruction algorithms based on deep learning: A survey. Computer Methods and Programs in Biomedicine, 238.
  3. Last, M. G. F., Voortman, L. M., & Sharp, T. H. (2023). scNodes: A correlation and processing toolkit for super-resolution fluorescence and electron microscopy. Nature Methods, 20, 1445-1446.
  4. (2023). Lightweight image super-resolution based on deep learning: State-of-the-art and future directions. Information Fusion, 94, 284-310.
  5. Wang, T., Sun, W., Qi, H., & Ren, P. (2018). Aerial image super-resolution via wavelet multiscale convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 15(5), 769-773.
  6. Wang, Z., Zhao, Y., & Chen, J. (2023). Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-Resolution. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, 2728-2740.
  7. Liu, B., Zhao, L., Liu, W., & Li, Y. (2024). MWLN: Multilevel Wavelet Learning Network for Continuous-Scale Remote-Sensing Image Super-Resolution. IEEE Geoscience and Remote Sensing Letters, 21, 1-5.
  8. Chen, H., Huang, L., Liu, T., & Ozcan, A. (2023). eFIN: Enhanced Fourier Imager Network for Generalizable Autofocusing and Pixel Super-Resolution in Holographic Imaging. IEEE Journal of Selected Topics in Quantum Electronics, 29(4), 1-10.
  9. Chen, Y., Liu, L., Phonevilay, V., et al. (2021). Image super-resolution reconstruction based on feature map attention mechanism. Applied Intelligence, 51, 4367–4380.
  10. Liu, B., & Chen, J. (2021). A Super Resolution Algorithm Based on Attention Mechanism and SRGANNetwork. IEEE Access, 9, 139138-139145.
  11. Yang, X., Li, X., Li, Z., & Zhou, D. (2021). Image super-resolution based on deep neural network of multiple attention mechanism. Journal of Visual Communication and Image Representation, 75.
  12. Liu, Y., Yang, D., Zhang, F., et al. (2023). Deep recurrent residual channel attention network for single image super-resolution. Visual Computer.
  13. Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., & Fu, Y. (2018). Proceedings of the European Conference on Computer Vision (ECCV), 286-301.
  14. Hsu, W. -Y., & Jian, P. -W. (2023). Wavelet Pyramid Recurrent Structure-Preserving Attention Network for Single Image Super-Resolution. IEEE Transactions on Neural Networks and Learning Systems.
  15. Dai, T., Cai, J., Zhang, Y., Xia, S.-T., & Zhang, L. (2019). Second-order attention network for single image super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 11065–11074.
  16. Zhang, Y., Li, K., Li, K., Zhong, B., & Fu, Y. (2019). Residual non-local attention networks for image restoration. arXiv preprint arXiv:1903.10082.
  17. Mei, Y., Fan, Y., Zhou, Y., Huang, L., Huang, T. S., & Shi, H. (2020). Image super-resolution with cross-scale non-local attention and exhaustive self-exemplars mining. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 5690–5699.
  18. Mei, Y., Fan, Y., & Zhou, Y. (2021). Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 3517-3526.
  19. Li, S., Tian, Y., Wang, C., Wu, H., & Zheng, S. (2023). Hyperspectral image super-resolution network based on cross-scale nonlocal attention. IEEE Transactions on Geoscience and Remote Sensing, 61, 1-15.
  20. Shan, L., Bai, X., Liu, C., et al. (2022). Super-resolution reconstruction of digital rock CT images based on residual attention mechanism. Advances in Geo-Energy Research, 6(2), 157-168. https://doi.org/10.6690/ager.2022.02.07
  21. Chen, Y., Xia, R., Yang, K., et al. (2024). MFFN: Image super-resolution via multi-level features fusion network. Visual Computer, 40, 489–504. https://doi.org/10.1007/s00371-023-02795-0
  22. An, T., Zhang, X., Huo, C., Xue, B., Wang, L., & Pan, C. (2022). TR-MISR: Multiimage super-resolution based on feature fusion with transformers. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 1373-1388.
  23. Niu, A., et al. (2022). MS2Net: Multi-scale and multi-stage feature fusion for blurred image super-resolution. IEEE Transactions on Circuits and Systems for Video Technology, 32(8), 5137-5150.
  24. Dargahi, S., Aghagolzadeh, A., & Ezoji, M. (2021). Single image super resolution using multi-path convolutional neural network. In 2021 5th International Conference on Pattern Recognition and Image Analysis (IPRIA) (pp. 1-6). Kashan, Iran.
  25. Wang, X., Wu, Y., Ming, Y., & Lv, H. (2020). Remote sensing imagery super resolution based on adaptive multi-scale feature fusion network. Sensors (Basel, Switzerland), 20.
  26. Avci, D., Sert, E., Dogantekin, E., Yildirim, O., Tadeusiewicz, R., & Plawiak, P. (2023). A new super resolution Faster R-CNN model based detection and classification of urine sediments. Biocybernetics and Biomedical Engineering, 43(1), 58-68.
  27. Li, G., Xing, W., Zhao, L., Lan, Z., Sun, J., Zhang, Z., Zhang, Q., Lin, H., & Lin, Z. (2023). Self-reference image super-resolution via pre-trained diffusion large model and window adjustable transformer. In Proceedings of the 31st ACM International Conference on Multimedia (MM '23) (pp. 7981–7992). Association for Computing Machinery.
  28. Chen, Z., Zhang, Y., Gu, J., Kong, L., & Yang, X. (2023). Recursive generalization transformer for image super-resolution. ArXiv. abs/2303.06373.