Facial attributes are important since they provide a detailed description and determine the visual appearance of human faces. In this paper, we aim at converting a face image to a sketch while simultaneously generating facial attributes. To this end, we propose a novel Attribute-Guided Sketch Generative Adversarial Network (ASGAN) which is an end to end framework and contains two pairs of generators and discriminators, one of which is used to generate faces with attributes while the other one is employed for image-to-sketch translation. The two generators form a W-shaped network (Wnet) and they are trained jointly with a weight-sharing constraint. Additionally, we also propose two novel discriminators, the residual one focusing on attribute generation and the triplex one helping to generate realistic looking sketches. To validate our model, we have created a new large dataset with 8,804 images, named the Attribute Face Photo & Sketch (AFPS) dataset which is the first dataset containing attributes associated to face sketch images. The experimental results demonstrate that the proposed network (i) generates more photo-realistic faces with sharper facial attributes than baselines and (ii) has good generalization capability on different generative tasks.

Attribute-guided sketch generation / Tang, H.; Chen, X.; Wang, W.; Xu, D.; Corso, J.; Sebe, N.; Yan, Yan. - (2019). (Intervento presentato al convegno IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019) tenutosi a Lille nel 14 -18 May 2019) [10.1109/FG.2019.8756586].

Attribute-guided sketch generation

H. Tang;W. Wang;D. Xu;N. Sebe;Y. Yan
2019-01-01

Abstract

Facial attributes are important since they provide a detailed description and determine the visual appearance of human faces. In this paper, we aim at converting a face image to a sketch while simultaneously generating facial attributes. To this end, we propose a novel Attribute-Guided Sketch Generative Adversarial Network (ASGAN) which is an end to end framework and contains two pairs of generators and discriminators, one of which is used to generate faces with attributes while the other one is employed for image-to-sketch translation. The two generators form a W-shaped network (Wnet) and they are trained jointly with a weight-sharing constraint. Additionally, we also propose two novel discriminators, the residual one focusing on attribute generation and the triplex one helping to generate realistic looking sketches. To validate our model, we have created a new large dataset with 8,804 images, named the Attribute Face Photo & Sketch (AFPS) dataset which is the first dataset containing attributes associated to face sketch images. The experimental results demonstrate that the proposed network (i) generates more photo-realistic faces with sharper facial attributes than baselines and (ii) has good generalization capability on different generative tasks.
2019
IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019)
New York
IEEE
978-1-7281-0089-0
Tang, H.; Chen, X.; Wang, W.; Xu, D.; Corso, J.; Sebe, N.; Yan, Yan
Attribute-guided sketch generation / Tang, H.; Chen, X.; Wang, W.; Xu, D.; Corso, J.; Sebe, N.; Yan, Yan. - (2019). (Intervento presentato al convegno IEEE International Conference on Automatic Face and Gesture Recognition (FG 2019) tenutosi a Lille nel 14 -18 May 2019) [10.1109/FG.2019.8756586].
File in questo prodotto:
File Dimensione Formato  
08756586.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.63 MB
Formato Adobe PDF
1.63 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/250755
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 19
  • ???jsp.display-item.citation.isi??? 12
social impact