Generating Artistic Portraits from Face Photos with Feature Disentanglement and Reconstruction

Public Deposited
Analytics

Downloadable Content

Download PDF
Request Version for Screen Reader
Creator
  • Guo H
    • Other Affiliation: School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China
  • Ma Z
    • Other Affiliation: Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, United States
  • Chen X
    • Affiliation: School of Information and Library Science
  • Wang X
    • Other Affiliation: Sage IT Consulting Group, Shanghai, China
  • Xu J
    • Other Affiliation: Advanced Manufacturing Technology Innovation Center, Guangzhou Institute of Technology, Xidian University, Guangzhou, China
  • Zheng Y
    • Other Affiliation: School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China
Abstract
  • Generating artistic portraits from face photos presents a complex challenge that requires high-quality image synthesis and a deep understanding of artistic style and facial features. Traditional generative adversarial networks (GANs) have made significant strides in image synthesis; however, they encounter limitations in artistic portrait generation, particularly in the nuanced disentanglement and reconstruction of facial features and artistic styles. This paper introduces a novel approach that overcomes these limitations by employing feature disentanglement and reconstruction techniques, enabling the generation of artistic portraits that more faithfully retain the subject’s identity and expressiveness while incorporating diverse artistic styles. Our method integrates six key components: a U-Net-based image generator, an image discriminator, a feature-disentanglement module, a feature-reconstruction module, a U-Net-based information generator, and a cross-modal fusion module, working in concert to transform face photos into artistic portraits. Through extensive experiments on the APDrawing dataset, our approach demonstrated superior performance in visual quality, achieving a significant reduction in the Fréchet Inception Distance (FID) score to 61.23, highlighting its ability to generate more-realistic and -diverse artistic portraits compared to existing methods. Ablation studies further validated the effectiveness of each component in our method, underscoring the importance of feature disentanglement and reconstruction in enhancing the artistic quality of the generated portraits.
Date of publication
Keyword
DOI
Identifier
Resource type
  • Article
Rights statement
  • In Copyright
License
  • Attribution 4.0 International
Journal title
  • Electronics (Switzerland)
Journal volume
  • 13
Journal issue
  • 5
Language
  • English
Version
  • Publisher
ISSN
  • 2079-9292
Publisher
  • Multidisciplinary Digital Publishing Institute (MDPI)

Relations

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details electronics-13-00955.pdf 2024-04-02 Public Download