SSFlow: Style-guided Neural Spline Flows for Face Image Manipulation

Hanbang Liang, Xianxu Hou, Linlin Shen

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

2 Citations (Scopus)

Abstract

Significant progress has been made in high-resolution and photo-realistic image generation by Generative Adversarial Networks (GANs). However, the generation process is still lack of control, which is crucial for semantic face editing. Furthermore, it remains challenging to edit target attributes and preserve the identity at the same time. In this paper, we propose SSFlow to achieve identity-preserved semantic face manipulation in StyleGAN latent space based on conditional Neural Spline Flows. To further improve the performance of Neural Spline Flows on such task, we also propose Constractive Squash component and Blockwise 1 x 1 Convolution layer. Moreover, unlike other conditional flow-based approaches that require facial attribute labels during inference, our method can achieve label-free manipulation in a more flexible way. As a result, our methods are able to perform well-disentangled edits along various attributes, and generalize well for both real and artistic face image manipulation. Qualitative and quantitative evaluations show the advantages of our method for semantic face manipulation over state-of-the-art approaches.

Original languageEnglish
Title of host publicationMM 2021 - Proceedings of the 29th ACM International Conference on Multimedia
PublisherAssociation for Computing Machinery, Inc
Pages79-87
Number of pages9
ISBN (Electronic)9781450386517
DOIs
Publication statusPublished - 17 Oct 2021
Externally publishedYes
Event29th ACM International Conference on Multimedia, MM 2021 - Virtual, Online, China
Duration: 20 Oct 202124 Oct 2021

Publication series

NameMM 2021 - Proceedings of the 29th ACM International Conference on Multimedia

Conference

Conference29th ACM International Conference on Multimedia, MM 2021
Country/TerritoryChina
CityVirtual, Online
Period20/10/2124/10/21

Keywords

  • face image editing
  • generative adversarial networks

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Software
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'SSFlow: Style-guided Neural Spline Flows for Face Image Manipulation'. Together they form a unique fingerprint.

Cite this