Abstract: Clear and high-quality images have become more and more necessary in recent years due to the rapid development of computer vision-based autonomous systems, including autonomous driving, underwater robots, video surveillance, and medical imaging. However, real-world circumstances, such as inclement weather, underwater scenes, and moving cameras, can lead to poorer-quality photographs. These degradations, which include color distortions, noise, and blurring, hurt how well visual systems accomplish tasks like target tracking, segmentation, and detection. Image restoration (IR) methods have proven essential to addressing these issues. Convolutional neural networks (CNNs) and generative adversarial networks (GANs), in particular, are two types of deep learning models that have shown promise as effective tools for improving image quality. This study explores advancements in edge preservation, denoising, and deblurring while examining a range of deep-learning techniques applied to image restoration... The study emphasizes how crucial it is to create effective IR methods to increase visual systems' capacity to adapt to complicated situations. In sectors including digital photography, medical imaging, and satellite data analysis, restoration of fine details in images has been greatly enhanced by the combination of classical and deep learning-based methods.

Keywords:Image Restoration, Deep Learning, Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), IR

🔒 This is a subscription article

Full text is available to subscribers and institutional members. Please choose an option below to access it.

• Zhai, L., Wang, Y., Cui, S., & Zhou, Y. (2023). A comprehensive review of deep learning-based real-world image restoration. IEEE Access, 11, 21049-21067.
• Vitale, S., Ferraioli, G., Pascazio, V., & Schirinzi, G. (2022). InSAR-MONet: Interferometric SAR phase denoising using a multiobjective neural network. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-14.
• Bai, H., Cheng, S., Tang, J., & Pan, J. (2021). Learning a cascaded non-local residual network for super-resolving blurry images. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 223-232).
• Hu, D., Zhang, Y., Liu, J., Du, C., Zhang, J., Luo, S., ... & Luo, L. (2021). SPECIAL: Single-shot projection error correction integrated adversarial learning for limited-angle CT. IEEE Transactions on Computational Imaging, 7, 734-746.
• Thepade, S. D., Patil, A. A., Nawale, C. M., Taralkar, C. D., & Suryavanshi, M. V. (2021, May). Appraise of deep learning and image processing based single image dehazing algorithms. In 2021 2nd International Conference for Emerging Technology (INCET) (pp. 1-7). IEEE.
• Wang, Q., Fan, H., Cong, Y., & Tang, Y. (2017, July). Single Image Super-resolution Using Spatial Transformer Networks. In 2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER) (pp. 564-567). IEEE.
• Neole, B. (2024). Application of Mathematical Modelling and Deep Learning in Image Restoration using Edge Preservation Method. Communications on Applied Nonlinear Analysis, 31(2s), 496-514.
• Deledalle, C. A., Denis, L., Tabti, S., & Tupin, F. (2017). MuLoG, or how to apply Gaussian denoisers to multi-channel SAR speckle reduction?. IEEE Transactions on Image Processing, 26(9), 4389-4403.
• Charles-Alban Deledalle, Lo¨ıc Denis, and Florence Tupin, “MuLoG: a generic variance-stabilization approach for speckle reduction in SAR interferometry and SAR polarimetry,” in IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2018, pp. 5816–5819.
• Denis, L., Deledalle, C. A., & Tupin, F. (2019, July). From patches to deep learning: Combining self-similarity and neural networks for SAR image despeckling. In IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium (pp. 5113-5116). IEEE.
• Cozzolino, D., Verdoliva, L., Scarpa, G., & Poggi, G. (2020). Nonlocal CNN SAR image despeckling. Remote Sensing, 12(6), 1006.
• Liu, P., Zhang, H., Zhang, K., Lin, L., & Zuo, W. (2018). Multi-level wavelet-CNN for image restoration. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 773-782).
• Pereg, D. (2024). One-Shot Image Restoration. arXiv preprint arXiv:2404.17426.
• Ouyang, X., Chen, Y., Zhu, K., & Agam, G. (2024). Image Restoration Refinement with Uformer GAN. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 5919-5928).
• Liu, J., Sun, Y., Xu, X., & Kamilov, U. S. (2019, May). Image restoration using total variation regularized deep image prior. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7715-7719). Ieee.
• Liang, J., Cao, J., Sun, G., Zhang, K., Van Gool, L., & Timofte, R. (2021). Swinir: Image restoration using swin transformer. In Proceedings of the IEEE/CVF international conference on computer vision(pp. 1833-1844).
• Liu, P. Y., & Lam, E. Y. (2018). Image reconstruction using deep learning. arXiv preprint arXiv:1809.10410.
• Zhang, K., Zuo, W., Gu, S., & Zhang, L. (2017). Learning deep CNN denoiser prior for image restoration. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3929-3938).
• Mao, X., Shen, C., & Yang, Y. B. (2016). Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. Advances in neural information processing systems, 29.
• Rivenson, Y., Zhang, Y., Günaydın, H., Teng, D., & Ozcan, A. (2018). Phase recovery and holographic image reconstruction using deep learning in neural networks. Light: Science & Applications, 7(2), 17141-17141.

Abstract: Clear and high-quality images have become more and more necessary in recent years due to the rapid development of computer vision-based autonomous systems, including autonomous driving, underwater robots, video surveillance, and medical imaging. However, real-world circumstances, such as inclement weather, underwater scenes, and moving cameras, can lead to poorer-quality photographs. These degradations, which include color distortions, noise, and blurring, hurt how well visual systems accomplish tasks like target tracking, segmentation, and detection. Image restoration (IR) methods have proven essential to addressing these issues. Convolutional neural networks (CNNs) and generative adversarial networks (GANs), in particular, are two types of deep learning models that have shown promise as effective tools for improving image quality. This study explores advancements in edge preservation, denoising, and deblurring while examining a range of deep-learning techniques applied to image restoration... The study emphasizes how crucial it is to create effective IR methods to increase visual systems' capacity to adapt to complicated situations. In sectors including digital photography, medical imaging, and satellite data analysis, restoration of fine details in images has been greatly enhanced by the combination of classical and deep learning-based methods.

Keywords:Image Restoration, Deep Learning, Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), IR

🔒 This is a subscription article

Full text is available to subscribers and institutional members. Please choose an option below to access it.

• Zhai, L., Wang, Y., Cui, S., & Zhou, Y. (2023). A comprehensive review of deep learning-based real-world image restoration. IEEE Access, 11, 21049-21067.
• Vitale, S., Ferraioli, G., Pascazio, V., & Schirinzi, G. (2022). InSAR-MONet: Interferometric SAR phase denoising using a multiobjective neural network. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-14.
• Bai, H., Cheng, S., Tang, J., & Pan, J. (2021). Learning a cascaded non-local residual network for super-resolving blurry images. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 223-232).
• Hu, D., Zhang, Y., Liu, J., Du, C., Zhang, J., Luo, S., ... & Luo, L. (2021). SPECIAL: Single-shot projection error correction integrated adversarial learning for limited-angle CT. IEEE Transactions on Computational Imaging, 7, 734-746.
• Thepade, S. D., Patil, A. A., Nawale, C. M., Taralkar, C. D., & Suryavanshi, M. V. (2021, May). Appraise of deep learning and image processing based single image dehazing algorithms. In 2021 2nd International Conference for Emerging Technology (INCET) (pp. 1-7). IEEE.
• Wang, Q., Fan, H., Cong, Y., & Tang, Y. (2017, July). Single Image Super-resolution Using Spatial Transformer Networks. In 2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER) (pp. 564-567). IEEE.
• Neole, B. (2024). Application of Mathematical Modelling and Deep Learning in Image Restoration using Edge Preservation Method. Communications on Applied Nonlinear Analysis, 31(2s), 496-514.
• Deledalle, C. A., Denis, L., Tabti, S., & Tupin, F. (2017). MuLoG, or how to apply Gaussian denoisers to multi-channel SAR speckle reduction?. IEEE Transactions on Image Processing, 26(9), 4389-4403.
• Charles-Alban Deledalle, Lo¨ıc Denis, and Florence Tupin, “MuLoG: a generic variance-stabilization approach for speckle reduction in SAR interferometry and SAR polarimetry,” in IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2018, pp. 5816–5819.
• Denis, L., Deledalle, C. A., & Tupin, F. (2019, July). From patches to deep learning: Combining self-similarity and neural networks for SAR image despeckling. In IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium (pp. 5113-5116). IEEE.
• Cozzolino, D., Verdoliva, L., Scarpa, G., & Poggi, G. (2020). Nonlocal CNN SAR image despeckling. Remote Sensing, 12(6), 1006.
• Liu, P., Zhang, H., Zhang, K., Lin, L., & Zuo, W. (2018). Multi-level wavelet-CNN for image restoration. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 773-782).
• Pereg, D. (2024). One-Shot Image Restoration. arXiv preprint arXiv:2404.17426.
• Ouyang, X., Chen, Y., Zhu, K., & Agam, G. (2024). Image Restoration Refinement with Uformer GAN. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 5919-5928).
• Liu, J., Sun, Y., Xu, X., & Kamilov, U. S. (2019, May). Image restoration using total variation regularized deep image prior. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7715-7719). Ieee.
• Liang, J., Cao, J., Sun, G., Zhang, K., Van Gool, L., & Timofte, R. (2021). Swinir: Image restoration using swin transformer. In Proceedings of the IEEE/CVF international conference on computer vision(pp. 1833-1844).
• Liu, P. Y., & Lam, E. Y. (2018). Image reconstruction using deep learning. arXiv preprint arXiv:1809.10410.
• Zhang, K., Zuo, W., Gu, S., & Zhang, L. (2017). Learning deep CNN denoiser prior for image restoration. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3929-3938).
• Mao, X., Shen, C., & Yang, Y. B. (2016). Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. Advances in neural information processing systems, 29.
• Rivenson, Y., Zhang, Y., Günaydın, H., Teng, D., & Ozcan, A. (2018). Phase recovery and holographic image reconstruction using deep learning in neural networks. Light: Science & Applications, 7(2), 17141-17141.