DGCA: high resolution image inpainting via DR-GAN and contextual attention

被引：4

作者：

Chen Y. ^{[1
]}

Xia R. ^{[2
,3
]}

Yang K. ^{[4
]}

Zou K. ^{[5
]}

机构：

[1] School of Computer Science and Engineering, Hunan University of Information Technology, Hunan, Changsha

[2] Mountain Yuelu Breeding Innovation Center Limited, Changsha

[3] Hunan Provincial Science and Technology Affairs Center, Changsha

[4] Hunan ZOOMLION Intelligent Technology Corporation Limited, Changsha

[5] Hunan WUJO High-Tech Material Corporation Limited, Loudi

来源：

Multimedia Tools and Applications | 2023年 / 82卷 / 30期

关键词：

Conditional generative adversarial network; Contextual attention; Deep learning; Image inpainting; Parallel network;

D O I：

10.1007/s11042-023-15313-0

中图分类号：

学科分类号：

摘要：

The most image inpainting algorithms often have existed problems such as blurred image, texture distortion and semantic inaccuracy, and the image inpainting effect is limited for images with large missing regions and resolution level. To solve above problems, the paper proposes an improved two-stage image inpainting network based on parallel network and contextual attention. Firstly, the improved deep residual network is used to perform generative pixels filling on the missing area, and the first-stage adversarial network is used to complete the edges information. Then, the color features of the filling map are extracted, the edge map is fused and complemented, and the fusion map is used as the conditional label of the second-stage adversarial network. Finally, the image repairing result has obtained through the two-stage network with the contextual attention module. The experiments on public datasets can show that the proposed algorithm can obtain a more realistic repairing effect. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

引用

页码：47751 / 47771

页数：20

共 42 条

[1]

Barnes C., Shechtman E., Finkelstein A., Goldman D., PatchMatch: A randomized correspondence algorithm for structural image editing, ACM Trans Graph, 28, 3, (2009)

[2]

Bertalmio M., Sapiro G., Caselles V., Ballester C., Image inpainting, Proceedings of the 27Th Annual Conference on Computer Graphics and Interactive Techniques, pp. 417-424, (2000)

[3]

Chen T., Zhang X., Hamann B., Wang D., Zhang H., A multi-level feature integration network for image inpainting, Multimed Tools Appl, 81, pp. 38781-38802, (2022)

[4]

Ding D., Ram S., Rodriguez J., Image inpainting using nonlocal texture matching and nonlinear filtering, IEEE Trans Image Process, 28, 4, pp. 1705-1709, (2019)

[5]

Doersch C., Singh S., Gupta A., Sivic J., Efros A., What makes Paris look like Paris?, ACM Trans Graphics, 31, 4, (2012)

[6]

Fang Y., Li Y., Tu X., Tan T., Wang X., Face completion with hybrid dilated convolution, Signal Process Image Commun, 80, (2020)

[7]

Gao S., Cheng M., Zhao K., Zhang X., Yang M., Torr P., Res2Net: a new multi-scale backbone architecture, IEEE Trans Pattern Anal Mach Intell, 43, 2, pp. 652-662, (2019)

[8]

Goodfellow I., Pouget-Abadie J., Mirza M., Xu B., Warde-Farley D., Ozair S., Courville A., Bengio Y., Generative adversarial nets, Proceedings of Advances in Neural Information Processing Systems, pp. 2672-2680, (2014)

[9]

Guo Q., Gao S., Zhang X., Yin Y., Zhang C., Patch-based image inpainting via two-stage low rank approximation, IEEE Trans Visual Comput Graphics, 24, 6, pp. 2023-2026, (2018)

[10]

Hu J., Shen L., Sun G., Squeeze-and-excitation networks, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132-7141, (2018)

← 1 2 3 4 5 →