%0 Journal Article
%A GUO Lei
%A LI Hai-jiang
%A LI Hong-song
%A WANG Wei-hua
%A LI Hai-yan
%T Two-Stage Network Inpainting Algorithm Based on BDCN and U-net Edge Generation
%D 2021
%R 10.13190/j.jbupt.2020-268
%J Journal of Beijing University of Posts and Telecommunications
%P 121-126
%V 44
%N 5
%X To repair the large irregular missing areas of an image, and obtain reasonable structure and fine-detailed textures,a two-stage network image inpainting algorithm based on bi-directional cascade network (BDCN) for perceptual edge detection and U-net incomplete edge generation is proposed. Firstly,the algorithm edges are extracted using the BDCN network. In the first stage,down-sampling is used to extract the features of the missing image edges based on the edge generation network of the U-net network architecture. The information inputted by the up-sampling layer and the information of each down-sampling layer is then combined to restore the image edge texture details. In the second stage,the hole convolution is applied for down-sampling and up-sampling,which adopts the residual network to reconstruct the missing image with rich details. The proposed algorithm is compared with the existing classic algorithm on the public datasets. Experimental results demonstrate that the proposed algorithm can obtain reasonable results and fine texture details,and its performance is superior to those of the contrast algorithms.
%U https://journal.bupt.edu.cn/EN/10.13190/j.jbupt.2020-268