MSMC-NET: IMAGE INPAINTING USING DEEP MULTI-SCALE AND MULTI-CONNECTION NETWORKS

被引：1

作者：

Wang, Miaohui ^{[1
]}

Chen, Xiaoming ^{[1
]}

Chen, Weiqian ^{[1
]}

Yuan, Yuan ^{[1
]}

机构：

[1] SZU, Coll Informat Engn, Guangdong Key Lab Intelligent Informat Proc, Shenzhen, Guangdong, Peoples R China

来源：

2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW) | 2019年

关键词：

Image inpainting; generative adversarial network; multi-scale and multi-connection network;

D O I：

10.1109/ICMEW.2019.00133

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Image inpainting is a hot research topic via deep learned features that can generate more reasonable structures and textures compared with traditional inpainting methods. In this work, we propose a generative adversarial network with multi-scale and multi-connection structure for image inpainting. Specifically, the proposed network consists of an edge generation network and a multi-scale image completion network with multi-connection structure. Experimental results show that our method outperforms state-of-the-arts on both ICME 2019 Grand Challenge and Places2 dataset.

引用

页码：683 / 686

页数：4

共 17 条

[1] Dual norms and image decomposition models [J].

Aujol, JF ;

Chambolle, A .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2005, 63 (01) :85-104

[2] Image inpainting [J].

Bertalmio, M ;

Sapiro, G ;

Caselles, V ;

Ballester, C .

SIGGRAPH 2000 CONFERENCE PROCEEDINGS, 2000, :417-424

[3] Nontexture inpainting by curvature-driven diffusions [J].

Chan, TF .

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2001, 12 (04) :436-449

[4] Region filling and object removal by exemplar-based image inpainting [J].

Criminisi, A ;

Pérez, P ;

Toyama, K .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (09) :1200-1212

[5] What Makes Paris Look like Paris? [J].

Doersch, Carl ;

Singh, Saurabh ;

Gupta, Abhinav ;

Sivic, Josef ;

Efros, Alexei A. .

ACM TRANSACTIONS ON GRAPHICS, 2012, 31 (04)

[6]

Efros A. A., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1033, DOI 10.1109/ICCV.1999.790383

[7] Globally and Locally Consistent Image Completion [J].

Iizuka, Satoshi ;

Simo-Serra, Edgar ;

Ishikawa, Hiroshi .

ACM TRANSACTIONS ON GRAPHICS, 2017, 36 (04)

[8] Image Inpainting for Irregular Holes Using Partial Convolutions [J].

Liu, Guilin ;

Reda, Fitsum A. ;

Shih, Kevin J. ;

Wang, Ting-Chun ;

Tao, Andrew ;

Catanzaro, Bryan .

COMPUTER VISION - ECCV 2018, PT XI, 2018, 11215 :89-105

[9] DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations [J].

Liu, Ziwei ;

Luo, Ping ;

Qiu, Shi ;

Wang, Xiaogang ;

Tang, Xiaoou .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :1096-1104

[10]

Nazeri K., 2019, EdgeConnect: generative image inpainting with adversarial edge learning

← 1 2 →