Multi-Directional Subspace Editing in Style-Space
Not on the map. Why?
Abstract (arXiv)
This paper describes a new technique for finding disentangled semantic directions in the latent space of StyleGAN. Our method identifies meaningful orthogonal subspaces that allow editing of one human face attribute, while minimizing undesired changes in other attributes. Our model is capable of editing a single attribute in multiple directions, resulting in a range of possible generated images. We compare our scheme with three state-of-the-art models and show that our method outperforms them in terms of face editing and disentanglement capabilities. Additionally, we suggest quantitative measures for evaluating attribute separation and disentanglement, and exhibit the superiority of our model with respect to those measures.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 24 of its 32 references that are in the map. First posted on arXiv 21 Nov 2022.
Builds on
24 of 32 references.
References · 24
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2013Auto-Encoding Variational Bayescited by 4,053
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
- 2021Alias-Free Generative Adversarial Networkscited by 1,184
- 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
- 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
- 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
- 2020GANSpace: Discovering Interpretable GAN Controlscited by 614
- 2021Designing an Encoder for StyleGAN Image Manipulationcited by 544
12 more
- 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
- 2020Closed-Form Factorization of Latent Semantics in GANscited by 408
- 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 394
- 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
- 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 349
- 2020StyleRig: Rigging StyleGAN for 3D Control over Portrait Imagescited by 268
- 2019On the "steerability" of generative adversarial networkscited by 248
- 2019GANalyze: Toward Visual Definitions of Cognitive Image Propertiescited by 193
- 2017Optimizing the Latent Space of Generative Networkscited by 157
- 2020Adversarial Latent Autoencoderscited by 155
- 2020img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimationcited by 58
- 2021Multi-Attribute Balanced Sampling for Disentangled GAN Controlscited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.