Abstract | ||
---|---|---|
StyleGANs have shown impressive results on data generation and manipulation in recent years, thanks to its disentangled style latent space. A lot of efforts have been made in inverting a pretrained generator, where an encoder is trained ad hoc after the generator is trained in a two-stage fashion. In this paper, we focus on style-based generators asking a scientific question: Does forcing such a generator to reconstruct real data lead to more disentangled latent space and make the inversion process from image to latent space easy? We describe a new methodology to train a style-based autoencoder where the encoder and generator are optimized end-to-end. We show that our proposed model consistently outperforms baselines in terms of image inversion and generation quality. Supplementary, code, and pretrained models are available on the project website(1). |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/WACV51458.2022.00103 | 2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022) |
DocType | ISSN | Citations |
Conference | 2472-6737 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ligong Han | 1 | 5 | 2.44 |
Sri Harsha Musunuri | 2 | 0 | 0.34 |
Martin Renqiang Min | 3 | 0 | 2.03 |
Ruijiang Gao | 4 | 2 | 2.39 |
Yu Tian | 5 | 0 | 0.34 |
Dimitris N. Metaxas | 6 | 8834 | 952.25 |