Multi-channel Image Inpainting Algorithm Based on Edge Prediction

被引:0
作者
Liu, Jianwen [1 ,2 ,3 ]
Yang, Ying [1 ,2 ,3 ]
Zhang, Juan [2 ,3 ]
Zhou, Mingquan [2 ,3 ]
Xue, Jiarui [1 ]
机构
[1] Shaanxi Normal Univ, Sch Comp Sci, Xian 710062, Peoples R China
[2] Shaanxi Normal Univ, Sch Journalism & Commun, Xian 710062, Peoples R China
[3] Shaanxi Normal Univ, Culture Educ Intelligent & Commun Engn Technol Re, Xian 710062, Peoples R China
来源
THIRTEENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2021) | 2022年 / 12083卷
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Image Inpainting; DCGAN; Gated Convolution; Multi-channel; Deep Learning;
D O I
10.1117/12.2623237
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
This paper considers how to restore an image with large stained areas. An end to end model is proposed, which contains two networks, an edge generation adversarial network and a content generative adversarial network. First, the edge generation adversarial network is deployed to infer the missing boundaries of the image. Then the second network with a designed edge information channel is employed to restore the missing or stained areas of the image with the guidance of the inferred boundaries. Experiments were performed on ImageNet. The results show that the proposed model can better understand the semantic information of the stained area by introducing additional object contour channels and greatly improve the inpainting capability of the model. Quantitative evaluation indexes show that the proposed model is 4.5% better than the DeepFill V2 model in structural similarity and 7.1% better than the DeepFill V2 model in Peak Signal-to-Noise Ratio.
引用
收藏
页数:9
相关论文
共 50 条
[31]   Image Inpainting Based Multi-scale Gated Convolution and Attention [J].
Jiang, Hualiang ;
Ma, Xiaohu ;
Yang, Dongdong ;
Zhao, Jiaxin ;
Shen, Yao .
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2022, PT II, 2022, 13530 :407-418
[32]   Image Inpainting Algorithm Based on Adaptive Template Direction [J].
Wu, Xuewen ;
Liu, Na ;
Song, Yunyun .
2013 6TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING (CISP), VOLS 1-3, 2013, :374-378
[33]   A new structure tensor based image inpainting algorithm [J].
Liu, Ying ;
Liu, Chanjuan ;
Zou, Hailin .
INTERNATIONAL JOURNAL OF GRID AND UTILITY COMPUTING, 2016, 7 (04) :294-303
[34]   Image inpainting network based on multi-level attention mechanism [J].
Xiang, Hongyue ;
Min, Weidong ;
Wei, Zitai ;
Zhu, Meng ;
Liu, Mengxue ;
Deng, Ziyang .
IET IMAGE PROCESSING, 2024, 18 (02) :428-438
[35]   Image Inpainting Algorithm Based on KSVD and Improved CDD [J].
Liu, Zexin ;
Wan, Wanggen .
2018 INTERNATIONAL CONFERENCE ON AUDIO, LANGUAGE AND IMAGE PROCESSING (ICALIP), 2018, :413-417
[36]   A Fast Image Inpainting Algorithm Based on TV Model [J].
Lu, Xiaobao ;
Wang, Weilan ;
Zhuoma, Duojie .
INTERNATIONAL MULTICONFERENCE OF ENGINEERS AND COMPUTER SCIENTISTS (IMECS 2010), VOLS I-III, 2010, :1457-+
[37]   Image inpainting algorithm based on double cross TV [J].
Zhai, Dong-Hai ;
Duan, Wei-Xia ;
Yu, Jiang .
Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China, 2014, 43 (03) :432-436
[38]   An Improved Exemplar-based Image Inpainting Algorithm [J].
Xiang, Chunyang ;
Duan, Pengsong ;
Cao, Yangjie ;
Shi, Lei .
2014 PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE & EDUCATION (ICCSE 2014), 2014, :770-775
[39]   A maximum-independent-set-based channel allocation algorithm for multi-channel wireless networks [J].
Yu, Xutao ;
Shi, Xiaoxiang ;
Zeng, Shaoxiang .
Journal of Southeast University (English Edition), 2015, 31 (01) :12-18
[40]   Research on Algorithm for Fast Image Inpainting Based on Exemplars [J].
Zhu, Shengfeng .
PROCEEDINGS OF THE 2018 3RD INTERNATIONAL WORKSHOP ON MATERIALS ENGINEERING AND COMPUTER SCIENCES (IWMECS 2018), 2018, 78 :226-230