E2F-GAN: Eyes-to-Face Inpainting via Edge-Aware Coarse-to-Fine GANs
Face inpainting is a challenging task aiming to ll the damaged or masked regions in face images with plausibly synthesized contents. Based on the given information, the reconstructed regions should look realistic and more importantly preserve the demographic and biometric properties of the individua...
| Authors: | , , , , , , |
|---|---|
| Format: | article |
| Publication Date: | 2022 |
| Country: | España |
| Institution: | Universidad Autónoma de Madrid |
| Repository: | Biblos-e Archivo. Repositorio Institucional de la UAM |
| Language: | English |
| OAI Identifier: | oai:repositorio.uam.es:10486/711186 |
| Online Access: | http://hdl.handle.net/10486/711186 https://dx.doi.org/10.1109/ACCESS.2022.3160174 |
| Access Level: | Open access |
| Keyword: | Face inpainting generative adversarial networks image inpainting Telecomunicaciones |
| Summary: | Face inpainting is a challenging task aiming to ll the damaged or masked regions in face images with plausibly synthesized contents. Based on the given information, the reconstructed regions should look realistic and more importantly preserve the demographic and biometric properties of the individual. The aim of this paper is to reconstruct the face based on the periocular region (eyes-to-face). To do this, we proposed a novel GAN-based deep learning model called Eyes-to-Face GAN (E2F-GAN) which includes two main modules: a coarse module and a re nement module. The coarse module along with an edge predictor module attempts to extract all required features from a periocular region and to generate a coarse output which will be re ned by a re nement module. Additionally, a dataset of eyes-to-face synthesis has been generated based on the public face dataset called CelebA-HQ for training and testing. Thus, we perform both qualitative and quantitative evaluations on the generated dataset. Experimental results demonstrate that our method outperforms previous learning-based face inpainting methods and generates realistic and semantically plausible images. We also provide the implementation of the proposed approach to support reproducible research via (https://github.com/amiretefaghi/E2F-GAN). INDEX |
|---|