Abstract
Single image deblurring is a significant and challenging task in image processing vision and machine learning. Convolutional Neural Network (CNN) based models for deblurring often have a complex structure and a considerable number of parameters compared with those for other image restoration tasks such as image denoising, dehazing and super-resolution. The main reason is the requirement of large reception fields, which are important to image deblurring due to possible large blur kernels. Dilated convolution is a useful way to increase reception field without adding extra parameters. In this paper, we propose a novel network by adopting a dilated convolution structure, and we further improve the training process by combining L1 loss, MS-SSIM loss and MSE loss. The proposed network is light and fast. Quantitative and qualitative experiments indicate that our method outperforms state-of-the-art models, in terms of performance and speed.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Chen, D., et al.: Gated context aggregation network for image dehazing and deraining. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1375–1383. IEEE (2019)
Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 379–387 (2016)
Gao, H., Tao, X., Shen, X., Jia, J.: Dynamic scene deblurring with parameter selective sharing and nested skip connections. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3848–3856 (2019)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)
Holschneider, M., Kronland-Martinet, R., Morlet, J., Tchamitchian, P.: A real-time algorithm for signal analysis with the help of the wavelet transform. In: Combes, J.M., Grossmann, A., Tchamitchian, P. (eds.) Wavelets, pp. 286–297. Springer, Heidelberg (1990). https://doi.org/10.1007/978-3-642-75988-8_28
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4700–4708 (2017)
Kalchbrenner, N., et al.: Video pixel networks. In: International Conference on Machine Learning, pp. 1771–1779 (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kupyn, O., Budzan, V., Mykhailych, M., Mishkin, D., Matas, J.: Deblurgan: blind motion deblurring using conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8183–8192 (2018)
Kupyn, O., Martyniuk, T., Wu, J., Wang, Z.: Deblurgan-v2: Deblurring (orders-of-magnitude) faster and better. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 8878–8887 (2019)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 2169–2178 (2006)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)
Lim, B., Son, S., Kim, H., Nah, S., Mu Lee, K.: Enhanced deep residual networks for single image super-resolution. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 136–144 (2017)
Liu, X., Suganuma, M., Sun, Z., Okatani, T.: Dual residual networks leveraging the potential of paired operations for image restoration. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7007–7016 (2019)
Nah, S., Hyun Kim, T., Mu Lee, K.: Deep multi-scale convolutional neural network for dynamic scene deblurring. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3883–3891 (2017)
Oord, A.v.d., et al.: Wavenet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)
Pan, J., et al.: Learning dual convolutional neural networks for low-level vision. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3070–3079 (2018)
Shen, Z., et al.: Human-aware motion deblurring. In: Proceedings of the IEEE Conference on Computer Vision (ICCV), pp. 5572–5581 (2019)
Tao, X., Gao, H., Shen, X., Wang, J., Jia, J.: Scale-recurrent network for deep image deblurring. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8174–8182 (2018)
Wang, Z., Ji, S.: Smoothed dilated convolutions for improved dense prediction. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2486–2495 (2018)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)
Zeng, Y., van der Lubbe, J.C., Loog, M.: Multi-scale convolutional neural network for pixel-wise reconstruction of van gogh’s drawings. Mach. Vis. Appl. 30(7–8), 1229–1241 (2019)
Zhang, J., et al.: Dynamic scene deblurring using spatially variant recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2521–2529 (2018)
Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a gaussian denoiser: Residual learning of deep CNN for image denoising. IEEE Trans. Image Process. 26(7), 3142–3155 (2017)
Zhang, S., He, F., Ren, W.: Photo-realistic dehazing via contextual generative adversarial networks. Mach. Vis. Appl. 31(5), 33 (2020)
Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss functions for image restoration with neural networks. IEEE Trans. Comput. Imaging 3(1), 47–57 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, B., Yin, H. (2021). DC-Deblur: A Dilated Convolutional Network for Single Image Deblurring. In: Yin, H., et al. Intelligent Data Engineering and Automated Learning – IDEAL 2021. IDEAL 2021. Lecture Notes in Computer Science(), vol 13113. Springer, Cham. https://doi.org/10.1007/978-3-030-91608-4_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-91608-4_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91607-7
Online ISBN: 978-3-030-91608-4
eBook Packages: Computer ScienceComputer Science (R0)