Geometric Style Transfer for Face Portraits

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

1 Scopus citations

Abstract

Geometric style transfer jointly stylizes the texture and geometry of a content image to better match a style image, which has attracted widespread attention due to its various applications. However, existing style transfer methods either primarily focus on texture and almost entirely ignore geometry, or have various drawbacks and are not suitable for Face Portraits. In the paper, We propose a new two-stage geometric style transfer method dedicated to face portraits, which simultaneously transfer both statistical and structural styles. Our network consists of Geometric deformation module (G) and Texture rendering module (T). G is trained with semantics image pairs, which has loose requirements on the training datasets. Besides, our flexible formulation also allows explicit user guidance and control of stylization tradeoffs. Experiments demonstrate that our method achieves state-of-the-art geometric style transfer for face portraits.

Original languageEnglish
Title of host publicationProceedings of the 5th ACM International Conference on Multimedia in Asia, MMAsia 2023
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9798400702051
DOIs
StatePublished - 6 Dec 2023
Externally publishedYes
Event5th ACM International Conference on Multimedia in Asia, MMAsia 2023 - Hybrid, Tainan, Taiwan, Province of China
Duration: 6 Dec 20238 Dec 2023

Publication series

NameProceedings of the 5th ACM International Conference on Multimedia in Asia, MMAsia 2023

Conference

Conference5th ACM International Conference on Multimedia in Asia, MMAsia 2023
Country/TerritoryTaiwan, Province of China
CityHybrid, Tainan
Period6/12/238/12/23

Keywords

  • Face portraits
  • Geometric deformation module (G)
  • Geometric style transfer
  • Texture rendering module (T)

Fingerprint

Dive into the research topics of 'Geometric Style Transfer for Face Portraits'. Together they form a unique fingerprint.

Cite this