Geometry-Aware GAN for Face Attribute Transfer

Danlan Huang, Xiaoming Tao, Jianhua Lu, Minh N. Do

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In this paper, the geometry-aware GAN is proposed to address the issue of facial attribute transfer with unpaired data. To tackle the unpaired training sample problem, the CycleGAN architecture is applied, where the bilateral mappings between the source and target domains are learned. The deformation flow is learned to capture the geometric variation between two domains. We first warp the source face into desired pose and shape according to the flow. Then, the transfer sub-network is designed to refine the results by hallucinating new components on the warped image. The attribute is removed by the reconstruction sub-network, coupled with the warping process. Experiments on benchmark demonstrate the advantages of our method compared to baselines.

Original languageEnglish (US)
Title of host publication2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
PublisherIEEE Computer Society
Number of pages5
ISBN (Electronic)9781538662496
StatePublished - Sep 2019
Event26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China
Duration: Sep 22 2019Sep 25 2019

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880


Conference26th IEEE International Conference on Image Processing, ICIP 2019
Country/TerritoryTaiwan, Province of China


  • Face generation
  • GAN
  • attribute transfer
  • geometry-aware
  • warping

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing


Dive into the research topics of 'Geometry-Aware GAN for Face Attribute Transfer'. Together they form a unique fingerprint.

Cite this