Unsupervised disentangling of appearance and geometry by deformable generator network

Xianglei Xing, Tian Han, Ruiqi Gao, Song Chun Zhu, Ying Nian Wu

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

25 Scopus citations

Abstract

We present a deformable generator model to disentangle the appearance and geometric information in purely unsupervised manner. The appearance generator models the appearance related information, including color, illumination, identity or category, of an image, while the geometric generator performs geometric related warping, such as rotation and stretching, through generating displacement of the coordinates of each pixel to obtain the final image. Two generators act upon independent latent factors to extract disentangled appearance and geometric information from image. The proposed scheme is general and can be easily integrated into different generative models. An extensive set of qualitative and quantitative experiments show that the appearance and geometric information can be well disentangled, and the learned geometric generator can be conveniently transferred to the other image datasets to facilitate knowledge transfer tasks.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Pages10346-10355
Number of pages10
ISBN (Electronic)9781728132938
DOIs
StatePublished - Jun 2019
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, United States
Duration: 16 Jun 201920 Jun 2019

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2019-June
ISSN (Print)1063-6919

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Country/TerritoryUnited States
CityLong Beach
Period16/06/1920/06/19

Keywords

  • And Body Pose
  • Deep Learning
  • Face
  • Gesture
  • Image and Video Synthesis
  • Representation Learning
  • Statistical Learning

Fingerprint

Dive into the research topics of 'Unsupervised disentangling of appearance and geometry by deformable generator network'. Together they form a unique fingerprint.

Cite this