Face Inpainting with Deep Generative Models

DOI

10.2991/ijcis.d.191016.003How to use a DOI?

Keywords

Face inpainting; Structural loss; Semantic inpainting; Deep generative models; GANs

Abstract

Semantic face inpainting from corrupted images is a challenging problem in computer vision and has many practical applications. Different from well-studied nature image inpainting, the face inpainting task often needs to fill pixels semantically into a missing region based on the available visual data. In this paper, we propose a new face inpainting algorithm based on deep generative models, which increases the structural loss constraint in the image generation model to ensure that the generated image has a structure as similar as possible to the face image to be repaired. At the same time, different weights are calculated in the corrupted image to enforce edge consistency at the repair boundary. Experiments on different face data sets and qualitative and quantitative analyses demonstrate that our algorithm is capable of generating visually pleasing face completions.

Copyright

© 2019 The Authors. Published by Atlantis Press SARL.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Zhenping Qiang
AU  - Libo He
AU  - Qinghui Zhang
AU  - Junqiu Li
PY  - 2019
DA  - 2019/10/25
TI  - Face Inpainting with Deep Generative Models
JO  - International Journal of Computational Intelligence Systems
SP  - 1232
EP  - 1244
VL  - 12
IS  - 2
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.d.191016.003
DO  - 10.2991/ijcis.d.191016.003
ID  - Qiang2019
ER  -