Adaptive Deep Learning Architectures for Enhanced Multi Degradation Image Super Resolution

International Journal of Electrical and Electronics Engineering

© 2025 by SSRG - IJEEE Journal

Volume 12 Issue 3

Year of Publication : 2025

Authors : Adam Muhudin, Osman Diriye Hussein, Abdullahi Mohamud Osoble, Abdirahman Abdullahi Omar

10.14445/23488379/IJEEE-V12I3P102

How to Cite?

Adam Muhudin, Osman Diriye Hussein, Abdullahi Mohamud Osoble, Abdirahman Abdullahi Omar, "Adaptive Deep Learning Architectures for Enhanced Multi Degradation Image Super Resolution," SSRG International Journal of Electrical and Electronics Engineering, vol. 12,  no. 3, pp. 13-20, 2025. Crossref, https://doi.org/10.14445/23488379/IJEEE-V12I3P102

Abstract:

This research addresses the limitations of existing Single Image Super Resolution (SISR) methods that typically target specific kinds of image deterioration, such as noised images or blurred images. These targeted approaches are ineffective in real-world scenarios where images suffer from multiple degradation types simultaneously. The proposed adaptive deep learning framework is designed to enhance the resolution of images affected by various degradation types, including noising, blurring, and compression artifacts. The proposed framework involves developing a multi-degradation modeling approach, adaptive feature learning mechanisms, tailored loss functions, and comprehensive datasets for effective training and evaluation. This unified solution aims to advance the state of the art in SISR by robustly handling diverse degradation types, thus improving image quality across a range of applications.

Keywords:

Single Image Super Resolution, Deep learning, Multi degradation, Image Restoration, Adaptive feature learning, Loss functions, Dataset construction.

References:

[1] Jae Woong Soh, and Nam Ik Cho, “Variational Deep Image Restoration,” IEEE Transactions on Image Processing, vol. 31, pp. 4363 4376, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Kai Cui et al., “Color Image Restoration Exploiting Inter Channel Correlation with a 3 Stage CNN,” IEEE Journal of Selected Topics in Signal Processing, vol. 15, no. 2, pp.174-189, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Wenhan Yang et al., “Deep Joint Rain Detection and Removal from a Single Image,” IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, pp. 1685-1694, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Chao Ren, Xiaohai He, and Truong Q. Nguyen, “Single Image Super Resolution via Adaptive High Dimensional Non-Local Total Variation and Adaptive Geometric Feature,” IEEE Transactions on Image Processing, vol. 26, no. 1, pp. 90-106, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Kai Zhang, Wangmeng Zuo, and Lei Zhang, “Learning a Single Convolutional Super Resolution Network for Multiple Degradations,” IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 3262-3271, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Kaiming He et al., “Deep Residual Learning for Image Recognition,” IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 770-778, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Chao Dong et al., “Image Super Resolution Using Deep Convolutional Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 2, pp. 295 307, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Wenzhe Shi et al., “Real Time Single Image and Video Super Resolution Using an Efficient Sub Pixel Convolutional Neural Network,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874-1883, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Jiwon Kim, Jung Kwon Lee, and Kyoung Mu Lee, “Accurate Image Super Resolution Using Very Deep Convolutional Networks,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 1646-1654, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Ying Tai, Jian Yang, and Xiaoming Liu, “Image Super Resolution via Deep Recursive Residual Network,” IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, pp. 2790 -2798, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Bee Lim yet al., “Enhanced Deep Residual Networks for Single Image Super Resolution,” IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, USA, pp. 1132-1140, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Radu Timofte et al., “NTIRE 2017 Challenge on Single Image Super Resolution: Methods and Results,” IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, USA, pp. 1110-1121, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Christian Ledig et al., “Photo Realistic Single Image Super Resolution Using a Generative Adversarial Network,” IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, pp. 105-114, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Richard Zhang, Phillip Isola, and Alexei A. Efros, “Split Brain Autoencoders: Unsupervised Learning by Cross Channel Prediction,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, pp. 645-654, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Xintao Wang et al., “ESRGAN: Enhanced Super Resolution Generative Adversarial Networks,” European Conference on Computer Vision, pp. 63-79, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Yulun Zhang et al., “Image Super Resolution Using Very Deep Residual Channel Attention Networks,” European Conference on Computer Vision, 2018, pp. 294-310.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Xintao Wang et al., “Recovering Realistic Texture in Image Super Resolution by Deep Spatial Feature Transform,” Proceedings of the European Conference on Computer Vision, pp. 606-615, 2018.
[Google Scholar] [Publisher Link]
[18] Yochai Blau, and Tomer Michaeli, “The Perception Distortion Tradeoff,” IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 6228-6237, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[19] D. Martin et al., “A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics,” Proceedings 8th IEEE International Conference on Computer Vision, Vancouver, BC, Canada, vol. 2, pp. 416-423, 2001.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Karen Simonyan, and Andrew Zisserman, “Very Deep Convolutional Networks for Large Scale Image Recognition,” International Conference on Learning Representations, pp. 1-14, 2015.
[Google Scholar] [Publisher Link]
[21] Jonathan Long, Evan Shelhamer, and Trevor Darrell, “Fully Convolutional Networks for Semantic Segmentation,” IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, pp. 3431-3440, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Takeru Miyato et al., “Spectral Normalization for Generative Adversarial Networks,” arXiv Preprint, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Richard Zhang, Phillip Isola, and Alexei A. Efros, “Colorful Image Colorization,” 14th European Conference on Computer Vision, Amsterdam, Netherlands, pp. 649-666, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Christian Szegedy et al., “Going Deeper with Convolutions,” IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, pp. 1-9, 2015.
[CrossRef] [Google Scholar] [Publisher Link]