Abstract
Single image blind motion deblurring refers to transferring a blurred motion image into a corresponding clear image, which is a challenging and classic problem in the field of computer vision. The spatially variant blur is usually caused by many factors, such as camera jitter and object motion. Since image deblurring can be regarded as the task of image transformation, deep learning methods based on coarse-to-fine scheme, especially those using multi-scale architectures become popular. However, they have the disadvantages of unsatisfactory image quality and time-consuming running caused by large kernel size. In this paper, we propose a novel end-to-end network structure based on Deep Hierarchical Multi-patch network architecture integrated with Context Module and additional ResBlocks in order to tackle deblurring problem. Compared with recently proposed networks, it generates images with better visual effect as well as higher image quality index. Besides, our model significantly reduces the test time. We evaluate the proposed network structure on public GoPro dataset, a large-scale image dataset with complex synthetic blur. The experiments on the benchmark dataset prove that our effective method outperforms other state-of-the-art blind deblurring algorithms both qualitatively and quantitatively, which demonstrates the effectiveness of Context Module in the task of single image blur removal.
Similar content being viewed by others
References
Hyun Kim T, Ahn B, Mu Lee K (2013) Dynamic scene deblurring. In: ICCV, pp 3160–3167
Sun J, Cao W, Xu Z, Ponce J (2015) Learning a convolutional neural network for non-uniform motion blur removal. In: CVPR, pp 769–777
Nah S, Hyun Kim T, Mu Lee K (2017) Deep multi-scale convolutional neural network for dynamic scene deblurring. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 257–265
Tao X, Gao H, Shen X, Wang J, Jia J (2018) Scale-recurrent network for deep image deblurring. In: CVPR, pp 8174–8182
Mei J, Wu Z, Chen X et al (2019) DeepDeblur: text image recovery from blur to sharp. Multim Tools Appl 78(13):18869–18885
Shen Z, Lai WS, Xu T, Kautz J, Yang MH (2018) Deep semantic face deblurring, pp 8260–8269. https://doi.org/10.1109/cvpr.2018.00862
Ren W, Zhang J, Ma L, Pan J, Cao X, Zuo W, LiuW, Yang M-S (2018) Deep non-blind deconvolution via generalized low-rank approximation. In: Advances in neural information processing systems, pp 295–305
Xiangyu Xu, Jinshan Pan, Yu-Jin Zhang, and Ming-HsuanYang. Motion blur kernel estimation via deep learning. IEEE Transactions on Image Processing, 27(1):194–205, 2018
Li L, Pan J, Lai W-S, Gao X, Sang N, Yang M-H (2018) Learning a discriminative prior for blind image deblurring. In: The IEEE conference on computer vision and pattern recognition (CVPR), June 2018
Chang C-F, Wu J-L (2014) A new single image deblurring algorithm using hyper laplacian priors. In: ICS, pp 1015–1022
Xu L, Zheng S, Jia J (2013) Unnatural l0 sparse representation for natural image deblurring. In: CVPR
Pan J, Sun D, Pfister H, Yang M-H (2016) Blind image deblurring using dark channel prior. In: CVPR
Cao Y, Wang S, Guo Z et al (2017) Synchronization of memristive neural networks with leakage delay and parameters mismatch via event-triggered control. Neural Netw 2019:119
Wang Shengbo, Cao Yuting, Huang Tingwen, Chen Yiran, Wen Shiping (2020) Event-triggered distributed control for synchronization of multiple memristive neural networks under cyber-physical attacks. Inf Sci 518:361–375
Xu L, Ren JSJ, Liu C, Jia J (2014) Deep convolutional neural network for image deconvolution. In: Proceedings of advance neural information processing system, pp 1790–1798
Gong D, Yang J, Liu L, Zhang Y, Reid ID, Shen C, Van Den Hengel A, Shi Q (2017) From motion blur to motion flow: a deep learning solution for removing heterogeneous motion blur. In: CVPR, 2017
Schuler CJ, Hirsch M, Harmeling S, Schölkopf B (2016) Learning to deblur. IEEE Trans Pattern Anal Mach Intell 38(7):1439–1451
Chakrabarti A (2016) A neural approach to blind motion deblurring. In: ECCV. Springer, pp 221–235
Gao H, Tao X, Shen X, Jia J (2019) Dynamic scene deblurring with parameter selective sharing and nested skip connections. CVPR 2019, pp 3848–3856
Ramakrishnan S, Pachori S, Gangopadhyay A, Raman S (2017) Deep generative filter for motion deblurring. In: 2017 IEEE international conference on computer vision workshops (ICCVW), pp 2993–3000
Isola P, Zhu J-Y, Zhou T (2016) Image-to-image translation with conditional adversarial networks
Kupyn O, Budzan V, Mykhailych M, Mishkin D, Matas J (2018) Deblurgan: blind motion deblurring using conditional adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8183–8192
Arjovsky M, Chintala S, Bottou L (2017) Wasserstein gan. arXiv:1701.07875
Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville AC (2017) Improved training of wasserstein gans. In: Advances in neural information processing systems, pp 5767–5777
Kupyn O, Martyniuk T, Wu J, Wang Z (2019) DeblurGAN-v2: deblurring (orders-of-magnitude) faster and better. CoRR arXiv:1908.03826
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp 770–778
Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of IEEE computer society conference on computer vision and pattern recognition. IEEE, pp 2169–2178
Zhang Hongguang, Dai Yuchao, Li Hongdong (2019) PiotrKoniusz. Deep stacked hierarchical multi-patch network for image deblurring with, IEEE Comput Vis Pattern Recognit (CVPR)
Chen LC, Papandreou G, Kokkinos I et al (2018) DeepLab: semantic Image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834
He K, Zhang X, Ren S et al (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intel 37(9):1904–1916
Noroozi M, Chandramouli P, Favaro P (2017) Motion deblurring in the wild. In: GCPR, 2017
Zhou S, Zhang J, Zuo W, Xie H, Pan J, Ren JS (2019) DAVANet: stereo deblurring with view aggregation. In: CVPR 2019, pp 10996–11005
Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. Eur Conf Comput Vis 1(4):5
Zhao H, Gallo O, Frosio I et al (2017) Loss functions for image restoration with neural networks. IEEE Trans Comput Imaging 3(1):47–57
Kohler R, Hirsch M, Mohler B, Scholkopf B, Harmeling S (2012) Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database. In: ECCV. Springer, pp 27–40
PyTorch. http://pytorch.org
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. Computer Science
Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feed forward neural networks. Aistats 9:249–256
Zhang J, Pan J, Ren J, Song Y, Bao L, Lau RWH, Yang M-H (2018) Dynamic scene deblurring using spatially variant recurrent neural networks. In: Proceedings of IEEE conference on computer vision pattern recognition, pp 2521–2529
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Tang, K., Xu, D., Liu, H. et al. Context Module Based Multi-patch Hierarchical Network for Motion Deblurring. Neural Process Lett 53, 211–226 (2021). https://doi.org/10.1007/s11063-020-10370-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-020-10370-0