Multi-Modal Face Stylization with a Generative Prior

No Thumbnail Available
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
In this work, we introduce a new approach for face stylization. Despite existing methods achieving impressive results in this task, there is still room for improvement in generating high-quality artistic faces with diverse styles and accurate facial reconstruction. Our proposed framework, MMFS, supports multi-modal face stylization by leveraging the strengths of StyleGAN and integrates it into an encoder-decoder architecture. Specifically, we use the mid-resolution and high-resolution layers of StyleGAN as the decoder to generate high-quality faces, while aligning its low-resolution layer with the encoder to extract and preserve input facial details. We also introduce a two-stage training strategy, where we train the encoder in the first stage to align the feature maps with StyleGAN and enable a faithful reconstruction of input faces. In the second stage, the entire network is fine-tuned with artistic data for stylized face generation. To enable the fine-tuned model to be applied in zero-shot and one-shot stylization tasks, we train an additional mapping network from the large-scale Contrastive-Language-Image-Pre-training (CLIP) space to a latent w+ space of fine-tuned StyleGAN. Qualitative and quantitative experiments show that our framework achieves superior performance in both one-shot and zero-shot face stylization tasks, outperforming state-of-the-art methods by a large margin.
Description

CCS Concepts: Computing methodologies -> Image processing

        
@article{
10.1111:cgf.14952
, journal = {Computer Graphics Forum}, title = {{
Multi-Modal Face Stylization with a Generative Prior
}}, author = {
Li, Mengtian
and
Dong, Yi
and
Lin, Minxuan
and
Huang, Haibin
and
Wan, Pengfei
and
Ma, Chongyang
}, year = {
2023
}, publisher = {
The Eurographics Association and John Wiley & Sons Ltd.
}, ISSN = {
1467-8659
}, DOI = {
10.1111/cgf.14952
} }
Citation
Collections