Image Quality Enhancement via Machine Learning: A Unified Approach to Super-Resolution, Denoising, and Low-Density Enhancement
DOI:
https://doi.org/10.47611/jsrhs.v12i4.5541Keywords:
Super-resolution, Low-density Enhancement, DenoisingAbstract
Problem: The escalating demand for high-quality images across various applications has underscored the necessity for advanced image enhancement techniques. Traditionally, denoising, super-resolution, and low-density enhancement, the three key image enhancement techniques, have been approached independently, resulting in separate developments for each. Unfortunately, a unified framework that seamlessly combines all three techniques and surpasses individual method performance has been lacking.
Proposed Idea: The objective of this research is to develop a unified image enhancement framework that not only unites these techniques but also substantiates its superiority over existing individual methods through an extensive series of experiments. The proposed method utilizes cascade autoencoder architectures to generate high-quality enhanced images. In addition, an auxiliary artifact type prediction module has been introduced to enhance the noise-awareness, resulting in improved accuracy.
Result: The proposed method demonstrates superior performance in achieving state-of-the-art accuracy when evaluated against three image quality metrics on various public datasets. Additionally, the practical application of the proposed method showcases its efficacy in effectively solving real-world problems.
Downloads
References or Bibliography
Agustsson, E., & Timofte, R. (2017). Ntire 2017 challenge on single image super-resolution: Dataset and study. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 126-135).
Anwar, S., & Barnes, N. (2019). Real image denoising with feature attention. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 3155-3164).
Dong, C., Loy, C. C., He, K., & Tang, X. (2015). Image super-resolution using deep convolutional networks. IEEE transactions on pattern analysis and machine intelligence, 38(2), 295-307.
Gu, S., Li, Y., Gool, L. V., & Timofte, R. (2019). Self-guided network for fast image denoising. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 2511-2520).
Guo, C., Li, C., Guo, J., Loy, C. C., Hou, J., Kwong, S., & Cong, R. (2020). Zero-reference deep curve estimation for low-light image enhancement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 1780-1789).
Guo, S., Yan, Z., Zhang, K., Zuo, W., & Zhang, L. (2019). Toward convolutional blind denoising of real photographs. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 1712-1722).
Jiang, Y., Gong, X., Liu, D., Cheng, Y., Fang, C., Shen, X., ... & Wang, Z. (2021). Enlightengan: Deep light enhancement without paired supervision. IEEE transactions on image processing, 30, 2340-2349.
Kim, J., Lee, J. K., & Lee, K. M. (2016). Accurate image super-resolution using very deep convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1646-1654).
Kim, Y., Soh, J. W., Park, G. Y., & Cho, N. I. (2020). Transfer learning from synthetic to real-noise denoising with adaptive instance normalization. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 3482-3492).
Lefkimmiatis, S. (2018). Universal denoising networks: a novel CNN architecture for image denoising. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3204-3213).
Lim, B., Son, S., Kim, H., Nah, S., & Mu Lee, K. (2017). Enhanced deep residual networks for single image super-resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 136-144).
Lim, S., & Kim, W. (2020). DSLR: Deep stacked Laplacian restorer for low-light image enhancement. IEEE Transactions on Multimedia, 23, 4272-4284.
Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision (pp. 2980-2988).
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016). Ssd: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14 (pp. 21-37). Springer International Publishing.
Lore, K. G., Akintayo, A., & Sarkar, S. (2017). LLNet: A deep autoencoder approach to natural low-light image enhancement. Pattern Recognition, 61, 650-662.
Loh, Y. P., & Chan, C. S. (2019). Getting to know low-light images with the exclusively dark dataset. Computer Vision and Image Understanding, 178, 30-42.
Plotz, T., & Roth, S. (2017). Benchmarking denoising algorithms with real photographs. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1586-1595).
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779-788).
Shi, W., Caballero, J., Huszár, F., Totz, J., Aitken, A. P., Bishop, R., ... & Wang, Z. (2016). Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1874-1883).
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4), 600-612.
Wei, C., Wang, W., Yang, W., & Liu, J. (2018). Deep retinex decomposition for low-light enhancement. arXiv preprint arXiv:1808.04560.
Yue, Z., Yong, H., Zhao, Q., Meng, D., & Zhang, L. (2019). Variational denoising network: Toward blind noise modeling and removal. Advances in neural information processing systems, 32.
Published
How to Cite
Issue
Section
Copyright (c) 2023 Woochan Jung; John Blofeld-Watson
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
