A Review of Image Restoration Based on Deep Learning
DOI:
https://doi.org/10.62051/meghns59Keywords:
Image Restoration; Deep Learning; Cue Learning; State Space Model.Abstract
Image restoration is a key task in the field of computer vision, which aims to recover high-quality clear images from degraded images. Degraded images may be produced for various reasons, such as noise, blurring, compression, etc. In recent years, the rapid development of deep learning technology has brought new breakthroughs in the field of image restoration, and various image restoration methods based on deep learning continue to emerge, and their performance is better than the previous GAN-based methods. Nevertheless, comprehensive and enlightening reviews of image restoration based on diffusion models are still scarce. This paper summarizes the latest research progress in image restoration in recent years, including cue learning, model scaling, generative prior, state space model, basic model and so on, and compares and analyzes their experimental results. Although the image restoration methods based on deep learning have achieved remarkable progress, there are still some challenges. Therefore, this paper analyzes the challenges in the field of image restoration and looks forward to the future research direction.
Downloads
References
[1] M. Chris, et al. Image quality assessment for determining efficacy and limitations of Super-Resolution Convolutional Neural Network (SRCNN). Applications of Digital Image Processing XL. Vol. 10396. SPIE, 2017.
[2] M. Kuriakose, EDSR: Empowering super-resolution algorithms with high-quality DIV2K images. Intelligent Decision Technologies 17.4 (2023): 1249 - 1263.
[3] Y. T. Hou, et al. The application of improved densenet algorithm in accurate image recognition. Scientific Reports 14.1 (2024): 8645.
[4] H. T. Chen, et al. pre-trained image processing transformer. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021.
[5] J. Y. Liang, et al. Swinir: Image restoration using swin transformer. Proceedings of the IEEE/CVF international conference on computer vision. 2021.
[6] V. H. G. Correa. Application of Real-ESRGAN in improving IR sensor Images for use in SAR operations. 2024.
[7] X. Q. Lin, et al. Diffbir: Toward blind image restoration with generative diffusion prior. European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2024.
[8] P. Vaishnav, et al. Promptir: Prompting for all-in-one blind image restoration. arXiv preprint arXiv: 2306.13090 2023.
[9] F. H. Yu, et al. "Scaling up to excellence: Practicing model scaling for photo-realistic image restoration in the wild." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024.
[10] Y. Shi, et al. Vmambair: Visual state space model for image restoration. IEEE Transactions on Circuits and Systems for Video Technology (2025).
[11] Y. N. Cui, et al. Omni-kernel network for image restoration. Proceedings of the AAAI conference on artificial intelligence. Vol. 38. No. 2. 2024.
[12] C. X. Ma, et al. Pretraining a foundation model for generalizable fluorescence microscopy-based image restoration. Nature Methods 21.8 (2024): 1558 - 1567.
[13] H. Guo, et al. Mambair: A simple baseline for image restoration with state-space model. European conference on computer vision. Cham: Springer Nature Switzerland, 2024.
[14] Y. T. Jiang, et al. Autodir: Automatic all-in-one image restoration with latent diffusion. European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2024.
[15] J. Kang, et al. Research on weed detection algorithm based on dynamic pruning neural network. Transactions of the Chinese Society for Agricultural Machinery. 54.04 (2023): 268 - 275.
[16] E. Alcaín, et al. Hardware architectures for real-time medical imaging. Electronics 10.24 (2021): 3118.
[17] S. Shen, et al. How much can clip benefit vision-and-language tasks? arXiv preprint arXiv: 2107.06383 (2021).
[18] Q. Y. Zhang, et al. Provable dynamic fusion for low-quality multimodal data. International conference on machine learning. PMLR, 2023.
[19] K. Y. Zhao, et al. A survey: Optimization and applications of evidence fusion algorithm based on Dempster–Shafer theory. Applied Soft Computing 124 (2022): 109075.
[20] B. Mildenhall, et al. Nerf: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM 65.1 (2021): 99 - 106.
[21] H. H. Chen, et al. Mvip-nerf: Multi-view 3d inpainting on nerf scenes via diffusion prior. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024.
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2025 Transactions on Computer Science and Intelligent Systems Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
