mlsanityData to 7 Oct 2026

Semantic and Geometric Unfolding of StyleGAN Latent Space

arXiv 2107.04481 ↗First posted 9 Jul 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks (GANs) have proven to be surprisingly efficient for image editing by inverting and manipulating the latent code corresponding to a natural image. This property emerges from the disentangled nature of the latent space. In this paper, we identify two geometric limitations of such latent space: (a) euclidean distances differ from image perceptual distance, and (b) disentanglement is not optimal and facial attribute separation using linear model is a limiting hypothesis. We thus propose a new method to learn a proxy latent representation using normalizing flows to remedy these limitations, and show that this leads to a more efficient space for face image editing.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 36 references that are in the map. First posted on arXiv 9 Jul 2021.

Builds on

27 of 36 references.

References · 27

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  8. 2017Improved Training of Wasserstein GANscited by 2,223
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  10. 2016Density estimation using Real NVPcited by 2,029
  11. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  12. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
15 more
  1. 2016Least Squares Generative Adversarial Networkscited by 1,000
  2. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  3. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  4. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  5. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  6. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  7. 2018Disentangling by Factorisingcited by 614
  8. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 584
  9. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  10. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  11. 2020Editing in Style: Uncovering the Local Semantics of GANscited by 183
  12. 2020Generative Hierarchical Features from Synthesizing Imagescited by 83
  13. 2019InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANscited by 16
  14. 2020Frequency Domain-based Perceptual Loss for Super Resolutioncited by 7
  15. 2021Unsupervised Disentanglement of Linear-Encoded Facial Semanticscited by 7

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1.

3 papers.

  1. 2022Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editabilitycited by 7
  2. 2022Learning Representations for Masked Facial Recoverycited by 0
  3. 2023TextCLIP: Text-Guided Face Image Generation And Manipulation Without Adversarial Trainingcited by 0