Image Inpainting Based on Multi-Level Feature Aggregation Network for Future Internet
-
Published:2023-09-28
Issue:19
Volume:12
Page:4065
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Wang Dong1ORCID, Hu Liuqing2, Li Qing1, Wang Guanyi2, Li Hongan23
Affiliation:
1. Institute of Scientific and Technical Information of China, Beijing 100038, China 2. College of Computer Science and Technology, Xi’an University of Science and Technology, Xi’an 710054, China 3. State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, China
Abstract
(1) Background: In the future Internet era, clarity and structural rationality are important factors in image inpainting. Currently, image inpainting techniques based on generative adversarial networks have made great progress; however, in practical applications, there are still problems of unreasonable or blurred inpainting results for high-resolution images and images with complex structures. (2) Methods: In this work, we designed a lightweight multi-level feature aggregation network that extracts features from convolutions with different dilation rates, enabling the network to obtain more feature information and recover more reasonable missing image content. Fast Fourier convolution was designed and used in the generative network, enabling the generator to consider the global context at a shallow level, making it easier to perform high-resolution image inpainting tasks. (3) Results: The experiment shows that the method designed in this paper performs well in geometrically complex and high-resolution image inpainting tasks, providing a more reasonable and clearer inpainting image. Compared with the most advanced image inpainting methods, our method outperforms them in both subjective and objective evaluations. (4) Conclusions: The experimental results indicate that the method proposed in this paper has better clarity and more reasonable structural features.
Funder
Natural Science Basis Research Plan in Shaanxi Province of China Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference32 articles.
1. Local deep-feature alignment for unsupervised dimension reduction;Zhang;IEEE Trans. Image Process.,2018 2. Deep multimodal distance metric learning using click constraints for image ranking;Yu;IEEE Trans. Cybern.,2016 3. Suvorov, R., Logacheva, E., Mashikhin, A., Remizova, A., Ashukha, A., Silvestrov, A., Kong, N., Goka, H., Park, K., and Lempitsky, V. (2022, January 3–8). Resolution-robust large mask inpainting with fourier convolutions. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA. 4. Levin, A., Zomet, A., Peleg, S., and Weiss, Y. (2004, January 11–14). Seamless image stitching in the gradient domain. Proceedings of the ECCV, Prague, Czech Republic. 5. Hui, Z., Li, J., Wang, X., and Gao, X. (2020). Image fine-grained inpainting. arXiv.
|
|