Generative Image Inpainting with Multi-Stage Decoding Network

被引：0

作者：

Liu W.-R. ^{[1
]}

Mi Y.-C. ^{[1
]}

Yang F. ^{[1
]}

Zhang Y. ^{[1
]}

Guo H.-L. ^{[2
]}

Liu Z.-M. ^{[1
]}

机构：

[1] College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou

[2] State Key Laboratory of Large Electric Drive System and Equipment Technology, Tianshui

来源：

Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2022年 / 50卷 / 03期

关键词：

Automatic encoding and decoding networks; Image inpainting; Multi-stage decoding network;

D O I：

10.12263/DZXB.20201451

中图分类号：

学科分类号：

摘要：

Current image inpainting methods mainly rely on automatic encoding and decoding networks. These methods try to use the information compressed in the encoding stage to restore an original image in the decoding stage. While, it is difficult to reconstruct detailed inpainting results by using only compressed information. Due to the loss of information during compression, there are visual artifacts in the results, such as blurring and obvious edge response around the reconstructed area. Aimed at the problem of incomplete utilization of image information, this manuscript proposed a multi-stage decoding network (MSDN). The MSDN decodes and aggregates features of each layer in the encoder by multiple decoders successively, which can increase utilization of features from different layers in the encoding stage and obtain better feature maps to reflect the defected area. The experiment results, which are conducted on internationally recognized datasets, show that visual effects of images generated by MSDN have been improved. © 2022, Chinese Institute of Electronics. All right reserved.

引用

页码：625 / 636

页数：11

共 35 条

[1] ELHARROUSS O, ALMAADEED N, Et al., Image inpainting: a review[J], Neural Processing Letters, 51, 2, pp. 2007-2028, (2020)
[2] Coloma Ballester, BERTALMIO M, CASELLES V, Et al., Filling-in by joint interpolation of vector fields and gray levels, IEEE Transactions on Image Processing, 10, 2, (2001)
[3] ASHIKHMIN M., Synthesizing natural textures, Proceedings of the 2001 symposium on Interactive 3D graphics - SI3D＇01, pp. 217-226, (2001)
[4] CONNELLY B, ELI S, ADAM F, Et al., Patchmatch: a randomized correspondence algorithm for structural image editing, ACM Transactions on Graphics, 28, 3, (2009)
[5] Ruzic Tijana, Pizurica Aleksandra, Context-aware patch-based image inpainting using markov random field modeling, IEEE Trans Image Process, 24, 1, (2015)
[6] LI Zhi-dan, HE Hong-jie, YIN Zhong-ke, Et al., Exemplar based image inpainting algorithm using direction features of curvelet transform, Acta Electronica Sinica, 44, 1, (2016)
[7] WU Xiao-jun, LI Gong-qing, Large scale image inpainting based on exemplar and structure information, Acta Electronica Sinica, 40, 8, pp. 1509-1514, (2012)
[8] 24, (2019)
[9] (2020)
[10] (2015)

← 1 2 3 4 →