Super-Resolution of Lightweight Images Based on Deep Learning
DOI:
https://doi.org/10.54097/f8y87181Keywords:
Deep Learning; Image Super Resolution.Abstract
As digital imaging technology advances, a significant breakthrough is the emergence of super-resolution technology, a method to enhance the quality of low-resolution images to high-resolution. When there are some developing of the newest digital camera's skills, the super-resolution technology is appearing and getting more and more importance. In the simplest terms, the image super-resolution skill is the technology of which one cover the process from low resolution images to high resolution images skills. This technology differs from the traditional approach in that it is attracting more and more attention from researchers and practitioners. This method is important in the future. With the passage of time, it will be more and more mature. In this paper, we focus on how to improve image resolution by using various technologies, and summarise the results obtained in recent years. Then, we briefly introduce the background and development of super resolution, then briefly introduce the technology. Finally, we come to a few conclusions regarding Deep Learning.
Downloads
References
Dai D X, Wang Y J, Chen Y H, et al. Is image super-resolution helpful for other vision tasks? [C]//2016 IEEEWinter Conference on Applications of Computer Vision.Lake Placid: IEEE, 2016: 1-9
Bei Y J, Damian A, Hu S J, et al. New techniques for preserving global structure and denoising with low information loss in single-image super-resolution[C]//2018 IEEE/CVF Conference on Computer Vision and PatternRecognition Workshops (CVPRW). Salt Lake City: IEEE,2018: 987-9877
Elsken T, Metzen J H, Hutter F. Neutral architecture search: Asurvey. Journal of Machine Learning Research, 2019, 20(55):1-21
Gou J, Yu B, Maybank S J, Tao D. Knowledge distillation: A survey. arXiv preprint arXiv:2006. 2020, 05525,
Keys R. Cubic convolution interpolation for digital image processing [J]. IEEE Transactions on Acoustics,Speech, and Signal Processing, 1981, 29(6): 1153-1160
Zhang K, Zuo W M, Zhang L. Learning a single convolutional super-resolution network for multiple degradations [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 3262-3271
Bevilacqua M, Roumy A, Guillemot C, et al. Low-complexity single-image super-resolution based on nonnegative neighbour embedding[C]//Proceedings of the British Machine Vision Conference 2012. Guildford: BMVA Press, 2012, 135: 10
Zhang Y B, Liu S Y, Dong C, et al. Multiple cycle-in-cycle generative adversarial networks for unsupervised image super-resolution [J]. IEEE Transactions on Image Processing, 2020, 29: 1101-1112
Lugmayr A, Danelljan M, Timofte R, et al.AIM 2019 challenge on real-world image super-resolution: Methods and results [C]//2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Seoul: IEEE, 2019: 3575-3583
Lu Z, Liu H, Li J, et al. Efficient transformer for single image super-resolution [EB/OL]. https://arxiv.org/abs/2108.11084
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
