Abstract
The rapid development of deep learning has brought a new development direction for image inpainting, changing the traditional image inpaiting algorithm, which can only repair the problem of small area damage based on the structure and texture of the damaged image. In recent years, image inpainting algorithm based on deep learning has received widespread attention from industry and academia so that it has made great progress. However, the current image inpainting algorithm based on deep learning still has the problem of consuming so much time. In order to solve the above problem, an end-to-end image inpainting algorithm suitable for real-time scene was proposed. The mask of the damaged image generated by D-linkNet network, the edge information of the damaged image, and damaged image were used to control the network input, which avoided the damage to the existing semantics of the image and retained the intact image outside the damaged. On this basis, in order to improve the performance of image inpainting, Convolutional Block Attention Module (CBAM) was used in the residual network. Experimental results show that, compared with edge information-based deep learning algorithm Edge Connect, the repair speed is twice as fast as Edge Connect while the repair results are similar.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Criminisi, A., Patrick, P., Kentaro, T.: Object removal by exemplar-based inpainting. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, USA, vol. 2 (2003)
Xu, Z., Sun, J.: Image inpainting by patch propagation using patch sparsity. IEEE Trans. Image Process. 19(5), 1153–1165 (2010)
Gao, C.Y., Xu, X.E., Luo, Y.M.: Object image restoration based on sparse representation. Chin. J. Comput. (9), 4 (2019)
Yu, J., Lin, Z., Yang, J.: Generative image inpainting with contextual attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New Zealand, pp. 5505–5514 (2018)
Nazeri, K., Ng, E., Joseph, T.: Edgeconnect: generative image inpainting with adversarial edge learning. arXiv preprint arXiv:1901.00212, 1901 (2019)
Goodfellow, I., Pouget-Abadie, J., Mirza, M.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Pathak, D., Krahenbuhl, P., Donahue, J.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, USA, pp. 2536–2544 (2016)
Yang, C., Lu, X., Lin, Z.: High-resolution image inpainting using multi-scale neural patch synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, USA, pp. 6721–6729 (2017)
Iizuka, S., Simo-Serra, E., Ishikawa, H.: Globally and locally consistent image completion. ACM Trans. Graph. (ToG) 36(4), 107 (2017)
Liu, G., Reda, F.A., Shih, K.J., Wang, T.-C., Tao, A., Catanzaro, B.: Image inpainting for irregular holes using partial convolutions. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 89–105. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_6
Zhou, L., Zhang, C., Wu, M.: D-LinkNet: LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction. In: Proceedings of CVPR Workshops, New Zealand, pp. 182–186 (2018)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Zhou, B., Lapedriza, A., Khosla, A.: Places: A 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1452–1464 (2017)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Qin, T., Liu, J., Xue, W. (2021). Research on Efficient Image Inpainting Algorithm Based on Deep Learning. In: Sun, X., Zhang, X., Xia, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2021. Lecture Notes in Computer Science(), vol 12736. Springer, Cham. https://doi.org/10.1007/978-3-030-78609-0_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-78609-0_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78608-3
Online ISBN: 978-3-030-78609-0
eBook Packages: Computer ScienceComputer Science (R0)