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 language | English (US) |
---|---|
Article number | 9366420 |
Pages (from-to) | 553-557 |
Number of pages | 5 |
Journal | IEEE Signal Processing Letters |
Volume | 28 |
DOIs | |
State | Published - 2021 |
All Science Journal Classification (ASJC) codes
- Signal Processing
- Applied Mathematics
- Electrical and Electronic Engineering
Keywords
- Deep learning
- generative adversarial networks
- image reconstruction
- latent code optimization