| Title |
Recovery of Mosaic Facial Images by Separate Training for Key Facial Attributes |
| Authors |
서동환(Donghwan Seo) ; 이준호(Juneho Yi) |
| DOI |
https://doi.org/10.5573/ieie.2020.57.5.87 |
| Keywords |
Image unmosaicing; Image completion; Image inpainting |
| Abstract |
In this paper, we propose a method to restore mosaic facial images so that the restored facial images can have not only correct semantic structure but also the same facial attributes as the ground truth. State-of-the-art methods produce plausible unmosaic facial images, but fail to correctly generate facial attributes such as glasses, hat and gender. To address this problem, we propose the idea of separate training for different facial attributes. For this, our network divides the training images into groups with the same facial attribute using a pretrained VGG-19 classifier and, trains a GAN based network that employs as many discriminators as the number of different facial attributes considered. Experimental results show that our model outperforms previous state-of-the-art methods in restoring the facial attributes considered. |