An Identity-Preserved Model for Face Sketch-Photo Synthesis

Face sketch-photo synthesis can be regarded as an image-to-image translation problem. Although many generative models achieve good translations from sketches to photos, they still have limitations in preserving face identity due to the huge modality gap of the two domains. To this end, we propose an...

Full description

Saved in:
Bibliographic Details
Published inIEEE signal processing letters Vol. 27; pp. 1095 - 1099
Main Authors Lin, Ye, Ling, Shenggui, Fu, Keren, Cheng, Peng
Format Journal Article
LanguageEnglish
Published New York IEEE 2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Discriminators
Domains
Face
Face recognition
Face sketch-photo synthesis
Feature extraction
Gallium nitride
generative adversarial networks
Generators
image generation
image-to-image translation
Sketches
Synthesis
Training
Translations
Online AccessGet full text

Cover

More Information
Summary:Face sketch-photo synthesis can be regarded as an image-to-image translation problem. Although many generative models achieve good translations from sketches to photos, they still have limitations in preserving face identity due to the huge modality gap of the two domains. To this end, we propose an identity-preserved adversarial model (IPAM), which includes an extended U-Net to increase the weight of the original sketch in translation, two discriminators focusing on the real or fake image concatenation of two domains to learn more styles of the target domain, and an identity constraint to request the fakes and the real targets to have zero cosine distance in feature space. We evaluate our method on two face sketch databases with face recognition. The results demonstrate our translation method is superior to the existing methods in maintaining face identity information.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2020.3005039