mlsanityData to 7 Oct 2026

AE-StyleGAN: Improved Training of Style-Based Auto-Encoders

arXiv 2110.08718 ↗First posted 17 Oct 2021cs.CV eess.IVcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 36 of its 41 references that are in the map. First posted on arXiv 17 Oct 2021.

Builds on

36 of 41 references.

References · 36

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  6. 2014Conditional Generative Adversarial Netscited by 2,152
  7. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  8. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  9. 2018VoxCeleb2: Deep Speaker Recognitioncited by 862
  10. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  11. 2016Generative Adversarial Text to Image Synthesiscited by 735
  12. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
24 more
  1. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  2. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  3. 2018Disentangling by Factorisingcited by 614
  4. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  5. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  6. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  7. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  8. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  9. 2016Adversarial Feature Learningcited by 350
  10. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 348
  11. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  12. 2016Adversarially Learned Inferencecited by 216
  13. 2020Editing in Style: Uncovering the Local Semantics of GANscited by 183
  14. 2020Adversarial Latent Autoencoderscited by 155
  15. 2016Invertible Conditional GANs for image editingcited by 118
  16. 2020HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histogramscited by 64
  17. 2021Negative Data Augmentationcited by 46
  18. 2018Image Colorization with Generative Adversarial Networkscited by 24
  19. 2018CR-GAN: Learning Complete Representations for Multi-view Generationcited by 23
  20. 2019Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisonscited by 9
  21. 2021Dual Projection Generative Adversarial Networks for Conditional Image Generationcited by 8
  22. 2020Unbiased Auxiliary Classifier GANs with MINEcited by 7
  23. 2020Learning Generative Models of Tissue Organization with Supervised GANscited by 6
  24. 2020Autoencoding Generative Adversarial Networkscited by 5

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 2.

5 papers.

  1. 2022SINE: SINgle Image Editing with Text-to-Image Diffusion Modelscited by 159
  2. 2023Improving Tuning-Free Real Image Editing with Proximal Guidancecited by 87
  3. 2022LatentSwap3D: Semantic Edits on 3D Image GANscited by 5
  4. 2022Overparameterization Improves StyleGAN Inversioncited by 4
  5. 2023Learning Pose Image Manifolds Using Geometry-Preserving GANs and Elasticaecited by 0