Journals / CMC / Vol.68, No.3
Table of Content

Research Article

BEST PAPER 2021

UFC-Net with Fully-Connected Layers and Hadamard Identity Skip Connection for Image Inpainting

Chung-Il Kim1, Jehyeok Rew2, Yongjang Cho2, Eenjun Hwang2,*
1 Korea Electronics Technology Institute, Seongnam, 13488, Korea
2 School of Electrical Engineering, Korea University, Seoul, 02841, Korea
* Corresponding Author: Eenjun Hwang. Email:
(This article belongs to this Special Issue: Machine Learning-based Intelligent Systems: Theories, Algorithms, and Applications)

Abstract

Image inpainting is an interesting technique in computer vision and artificial intelligence for plausibly filling in blank areas of an image by referring to their surrounding areas. Although its performance has been improved significantly using diverse convolutional neural network (CNN)-based models, these models have difficulty filling in some erased areas due to the kernel size of the CNN. If the kernel size is too narrow for the blank area, the models cannot consider the entire surrounding area, only partial areas or none at all. This issue leads to typical problems of inpainting, such as pixel reconstruction failure and unintended filling. To alleviate this, in this paper, we propose a novel inpainting model called UFC-net that reinforces two components in U-net. The first component is the latent networks in the middle of U-net to consider the entire surrounding area. The second component is the Hadamard identity skip connection to improve the attention of the inpainting model on the blank areas and reduce computational cost. We performed extensive comparisons with other inpainting models using the Places2 dataset to evaluate the effectiveness of the proposed scheme. We report some of the results.

Keywords

Image processing; computer vision; image inpainting; image restoration; generative adversarial nets
  • 617

    View

  • 561

    Download

  • 100

    Like

Share Link

WeChat scan