GANalyzer: Analysis and Manipulation of GANs Latent Space for Controllable Face Synthesis
Not on the map. Why?
Abstract (arXiv)
Generative Adversarial Networks (GANs) are capable of synthesizing high-quality facial images. Despite their success, GANs do not provide any information about the relationship between the input vectors and the generated images. Currently, facial GANs are trained on imbalanced datasets, which generate less diverse images. For example, more than 77% of 100K images that we randomly synthesized using the StyleGAN3 are classified as Happy, and only around 3% are Angry. The problem even becomes worse when a mixture of facial attributes is desired: less than 1% of the generated samples are Angry Woman, and only around 2% are Happy Black. To address these problems, this paper proposes a framework, called GANalyzer, for the analysis, and manipulation of the latent space of well-trained GANs. GANalyzer consists of a set of transformation functions designed to manipulate latent vectors for a specific facial attribute such as facial Expression, Age, Gender, and Race. We analyze facial attribute entanglement in the latent space of GANs and apply the proposed transformation for editing the disentangled facial attributes. Our experimental results demonstrate the strength of GANalyzer in editing facial attributes and generating any desired faces. We also create and release a balanced photo-realistic human face dataset. Our code is publicly available on GitHub.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 43 of its 58 references that are in the map. First posted on arXiv 2 Feb 2023.
Builds on
43 of 58 references.
References · 43
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2022Generative Adversarial Networkscited by 5,603
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
- 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
- 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
- 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
- 2021Alias-Free Generative Adversarial Networkscited by 1,181
31 more
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
- 2018Self-Attention Generative Adversarial Networkscited by 809
- 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
- 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
- 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
- 2020In-Domain GAN Inversion for Real Image Editingcited by 420
- 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
- 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
- 2018Video-to-Video Synthesiscited by 388
- 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 288
- 2019Few-shot Video-to-Video Synthesiscited by 196
- 2020Semantic Photo Manipulation with a Generative Image Priorcited by 178
- 2017Latent Space Oddity: on the Curvature of Deep Generative Modelscited by 169
- 2016Semantic Image Inpainting with Deep Generative Modelscited by 156
- 2019RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolutioncited by 145
- 2017BEGAN: Boundary Equilibrium Generative Adversarial Networkscited by 121
- 2017Fader Networks: Manipulating Images by Sliding Attributescited by 118
- 2020Controlling generative models with continuous factors of variationscited by 93
- 2017The Riemannian Geometry of Deep Generative Modelscited by 81
- 2016Deep Feature Interpolation for Image Content Changescited by 80
- 2018The Unusual Effectiveness of Averaging in GAN Trainingcited by 73
- 2020World-Consistent Video-to-Video Synthesiscited by 69
- 2017On the regularization of Wasserstein GANscited by 65
- 2017Metrics for Deep Generative Modelscited by 53
- 2020Navigating the GAN Parameter Space for Semantic Image Editingcited by 49
- 2018Sequential Attention GAN for Interactive Image Editingcited by 33
- 2020ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Networkcited by 27
- 2021Surrogate Gradient Field for Latent Space Manipulationcited by 12
- 2021ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimationcited by 10
- 2022ACR Loss: Adaptive Coordinate-based Regression Loss for Face Alignmentcited by 7
- 2021Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networkscited by 6
Built on by
Citing papers per year: 2024: 2.
2 papers.