Face Destylization

Fatemeh Shiri, Xin Yu, Piotr Koniusz, Fatih Porikli

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

7 Citations (Scopus)

Abstract

Numerous style transfer methods which produce artistic styles of portraits have been proposed to date. However, the inverse problem of converting the stylized portraits back into realistic faces is yet to be investigated thoroughly. Reverting an artistic portrait to its original photo-realistic face image has potential to facilitate human perception and identity analysis. In this paper, we propose a novel Face Destylization Neural Network (FDNN) to restore the latent photo-realistic faces from the stylized ones. We develop a Style Removal Network composed of convolutional, fully-connected and deconvolutional layers. The convolutional layers are designed to extract facial components from stylized face images. Consecutively, the fully-connected layer transfers the extracted feature maps of stylized images into the corresponding feature maps of real faces and the deconvolutional layers generate real faces from the transferred feature maps. To enforce the destylized faces to be similar to authentic face images, we employ a discriminative network, which consists of convolutional and fully connected layers. We demonstrate the effectiveness of our network by conducting experiments on an extensive set of synthetic images. Furthermore, we illustrate our network can recover faces from stylized portraits and real paintings for which the stylized data was unavailable during the training phase.

Original languageEnglish
Title of host publication2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
EditorsYi Guo, Manzur Murshed, Zhiyong Wang, David Dagan Feng, Hongdong Li, Weidong Tom Cai, Junbin Gao
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages427-434
Number of pages8
ISBN (Electronic)9781538628393
ISBN (Print)9781538628386
DOIs
Publication statusPublished - 2017
Externally publishedYes
EventDigital Image Computing Techniques and Applications 2017
- Novotel Sydney Manly Pacific , Sydney, Australia
Duration: 29 Nov 20171 Dec 2017
Conference number: 19th
http://dicta2017.dictaconference.org/
https://ieeexplore.ieee.org/xpl/conhome/8226656/proceeding (Proceedings)

Conference

ConferenceDigital Image Computing Techniques and Applications 2017
Abbreviated titleDICTA 2017
CountryAustralia
CitySydney
Period29/11/171/12/17
Internet address

Cite this