Inversion Based on a Detached Dual-Channel Domain Method for StyleGAN2 Embedding

Nan Yang, Mengchu Zhou, Bingjie Xia, Xiwang Guo, Liang Qi

Research output: Contribution to journalArticlepeer-review

Abstract

A style-based generative adversarial network (StyleGAN2) yields remarkable results in image-to-latent embedding. This work proposes a Detached Dual-channel Domain Encoder as an effective and robust method to embed an image to a latent code, i.e., GAN inversion. It infers a latent code from two aspects: a) a detached dual-channel design to support faithful image reconstruction; and b) a local skip connection that allows conveying pieces of information with image details. We further introduce a hierarchical progressive training strategy that allows the proposed encoder to separately capture different semantic features. The qualitative and quantitative experimental results show that the well-trained encoder can embed an image into a latent code in StyleGAN2 latent space with less time than its peers while preserving facial identity and image details well.

Original languageEnglish (US)
Article number9366420
Pages (from-to)553-557
Number of pages5
JournalIEEE Signal Processing Letters
Volume28
DOIs
StatePublished - 2021

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Keywords

  • Deep learning
  • generative adversarial networks
  • image reconstruction
  • latent code optimization

Fingerprint Dive into the research topics of 'Inversion Based on a Detached Dual-Channel Domain Method for StyleGAN2 Embedding'. Together they form a unique fingerprint.

Cite this