注意力机制引导的混合失真图像复原研究
Attention-Guided Image Restoration on Hybrid Distortion
DOI: 10.12677/CSA.2022.124079, PDF,    科研立项经费支持
作者: 龚敏学：成都信息工程大学，计算机学院，四川 成都；朱 烨：四川省图形图像与空间信息2011协同创新中心，四川 成都；符 颖*：成都信息工程大学，计算机学院，四川 成都;四川省图形图像与空间信息2011协同创新中心，四川 成都
关键词: 混合失真图像；图像复原；注意力机制 ；Hybrid-Distorted Images； Image Restoration； Attention Mechanism
摘要: 针对真实场景下多种混合失真组合的多任务图像复原，考虑到受不同退化机制影响的复原任务之间具有差异性和相似性，提出了一种由注意力机制引导的混合失真图像复原网络，该网络包含由任务驱动的操作层模块，利用注意力对不同退化机制的不同表现来解决混合失真这类多任务图像复原问题，从而更好地复原了受不同退化机制影响的图像。实验结果表明，相较于单任务复原模型，该方法对真实场景下混合失真组合图像的复原效果更佳。
Abstract: Aiming at the multi-task image restoration of multiple hybrid distortion combinations in real scenes, considering the differences and similarities between image restoration tasks affected by different degradation mechanisms, an attention-guided hybrid-distorted image restoration net-work is proposed, which contains a task-driven operation layer module to solve the hybrid distortion multi-task image restoration problem by using the different performance of attention mechanism on different degradation mechanisms. The experimental results showed that, compared with the single-task restoration models, the proposed method has a better restoration effect on hybrid-distorted images in real scenes.
文章引用：龚敏学, 朱烨, 符颖. 注意力机制引导的混合失真图像复原研究[J]. 计算机科学与应用, 2022, 12(4): 775-784. https://doi.org/10.12677/CSA.2022.124079

参考文献

[1] Perrone, D. and Favaro, P. (2014) Total Variation Blind Deconvolution: The Devil Is in the Details. 2014 IEEE Confer-ence on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 2909-2916. [Google Scholar] [CrossRef] 
[2] Fattal, R. (2007) Image Upsampling via Imposed Edge Statistics. ACM Transactions on Graphics, 26, 95-es. [Google Scholar] [CrossRef] 
[3] Yang, J., Wright, W., Huang, T.S. and Ma, Y. (2010) Image Su-per-Resolution via Sparse Representation. IEEE Transactions on Image Processing, 19, 2861-2873. [Google Scholar] [CrossRef] 
[4] Aharon, M., Elad, M. and Bruckstein, A. (2006) K-SVD: An Al-gorithm for Designing Overcomplete Dictionaries for Sparse Representation. Proc of the IEEE Transactions on Signal Processing, 54, 4311-4322. [Google Scholar] [CrossRef] 
[5] Xie, J., Xu, L. and Chen, E. (2012) Image Denoising and Inpaint-ing with Deep Neural Networks. Proceedings of the 26th Annual Conference on Advances in Neural Information Pro-cessing Systems, Lake Tahoe, 3-6 December 2012, 341-349.
[6] Zhang, K., Zuo, W. and Zhang, L. (2018) FFDNet: Toward a Fast and Flexible Solution for CNN Based Image Denoising. Proc of the IEEE Transactions on Image Pro-cessing, 27, 4608-4622. [Google Scholar] [CrossRef] 
[7] Zhang, K., Zuo, W., Zhang, L., Meng, D. and Zhang, L. (2017) Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. Proc of the IEEE Transactions on Image Processing, 26, 3142-3155. [Google Scholar] [CrossRef] 
[8] Kupyn, O., Budzan, V., Mykhailych, M., Mishkin, D. and Matas, J. (2018) Deblurgan: Blind Motion Deblurring Using Conditional Adversarial Networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 8183-8192. [Google Scholar] [CrossRef] 
[9] Sun, J., Cao, W., Xu, Z. and Ponce, J. (2015) Learning a Convo-lutional Neural Network for Non-Uniform Motion Blur Removal. Proc of IEEE Conference on Computer Vision and Pattern Recognition, Boston, 7-12 June 2015, 769-777. [Google Scholar] [CrossRef] 
[10] Yang, W., Robby, T.T., Feng, J., Liu, J., Guo, Z. and Yan, S. (2017) Deep Joint Rain Detection and Removal from a Single Image. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 1685-1694. https://arxiv.org/abs/1609.07769 [Google Scholar] [CrossRef] 
[11] Li, G., He, X., Zhang, W., Chang, H., Dong, L. and Lin, L. (2018) Non-Locally Enhanced Encoder-Decoder Network for Single Image De-Raining. Proceedings of the 26th ACM interna-tional conference on Multimedia, Seoul, 22-26 October 2018, 1056-1064. [Google Scholar] [CrossRef] 
[12] Zhang, X., Dong, H., Hu, Z., Lai, W.-S., Wang, F. and Yang, M.-H. (2020) Gated Fusion Network for Degraded Image Super Resolution. International Journal of Computer Vision, 128, 1699-1721. [Google Scholar] [CrossRef] 
[13] Yu, K., Dong, C., Lin, L. and Loy, C.C. (2018) Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 2443-2452. [Google Scholar] [CrossRef] 
[14] Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., et al. (2015) Going Deeper with Convolutions. IEEE/CVF Conference on Computer Vision and Pattern Recognition, Boston, 7-12 June 2015, 1-9. [Google Scholar] [CrossRef] 
[15] Loshchilov, I. and Hutter, F. (2016) SGDR: Stochastic Gradient Descent with Warm Restarts. 5th International Conference on Learning Representations, Toulon, 24-26 April 2016, arXiv preprint arXiv: 1608.03983.
[16] Quan, Y., Chen, M., Pang, T. and Ji, H. (2020) Self-2-Self with Dropout: Learning Self-Supervised Denoising from Single Image. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, 13-19 June 2020, 1887-1895. [Google Scholar] [CrossRef] 
[17] Suganuma, M., Liu, X. and Okatani, T. (2019) Atten-tion-Based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, 15-20 June 2019, 9031-9040. [Google Scholar] [CrossRef]