mlsanityData to 7 Oct 2026

Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning

arXiv 2004.11660 ↗First posted 24 Apr 2020cs.CVcited by 219

Not on the map. Why?

Cited by 24 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose DiscoFaceGAN, an approach for face image generation of virtual people with disentangled, precisely-controllable latent representations for identity of non-existing people, expression, pose, and illumination. We embed 3D priors into adversarial learning and train the network to imitate the image formation of an analytic 3D face deformation and rendering process. To deal with the generation freedom induced by the domain gap between real and rendered faces, we further introduce contrastive learning to promote disentanglement by comparing pairs of generated images. Experiments show that through our imitative-contrastive learning, the factor variations are very well disentangled and the properties of a generated face can be precisely controlled. We also analyze the learned latent space and present several meaningful properties supporting factor disentanglement. Our method can also be used to embed real images into the disentangled latent space. We hope our method could provide new understandings of the relationship between physical properties and deep image synthesis.

Key facts. Cited by 219 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 37; 2022: 53; 2023: 47; 2024: 53; 2025: 21; 2026: 8.

219 papers.

Sort:

By area:

  1. 2021Cross-Modal Contrastive Learning for Text-to-Image Generationcited by 259
  2. 2021Motion Representations for Articulated Animationcited by 253
  3. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  4. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 218
  5. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  6. 2021PIRenderer: Controllable Portrait Image Generation via Semantic Neural Renderingcited by 202
  7. 2022Depth-Aware Generative Adversarial Network for Talking Head Video Generationcited by 177
  8. 2024Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animationcited by 172
  9. 2021Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detectioncited by 133
  10. 2022RigNeRF: Fully Controllable Neural 3D Portraitscited by 126
  11. 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 124
  12. 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
38 more
  1. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
  2. 2021SynFace: Face Recognition with Synthetic Datacited by 106
  3. 2022Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesiscited by 93
  4. 2022DigiFace-1M: 1 Million Digital Face Images for Face Recognitioncited by 92
  5. 2021GAN-Control: Explicitly Controllable GANscited by 91
  6. 2024X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attentioncited by 88
  7. 2023IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Modelscited by 72
  8. 2022Knowledge Graph Contrastive Learning for Recommendationcited by 69
  9. 2022Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Productioncited by 61
  10. 2022ClipFace: Text-guided Editing of Textured 3D Morphable Modelscited by 59
  11. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58
  12. 2023Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Datacited by 55
  13. 2023StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Videocited by 52
  14. 2022AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatarscited by 46
  15. 2023Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Datacited by 44
  16. 2023DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatarscited by 42
  17. 2025Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animationcited by 41
  18. 2022Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Imagescited by 39
  19. 2023Synthetic Data for Face Recognition: Current State and Future Prospectscited by 38
  20. 2022Contrastive Meta Learning with Behavior Multiplicity for Recommendationcited by 37
  21. 2022Controllable 3D Face Synthesis with Conditional Generative Occupancy Fieldscited by 37
  22. 2021Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning Viewcited by 34
  23. 2023OmniAvatar: Geometry-Guided Controllable 3D Head Synthesiscited by 34
  24. 2024On the Challenges and Opportunities in Generative AIcited by 31
  25. 2021VariTex: Variational Neural Face Texturescited by 30
  26. 2023FreeDrag: Feature Dragging for Reliable Point-based Image Editingcited by 28
  27. 2022Finding Directions in GAN's Latent Space for Neural Face Reenactmentcited by 27
  28. 2022Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Modelscited by 27
  29. 2022Unsupervised Face Recognition using Unlabeled Synthetic Datacited by 27
  30. 2023Identity-driven Three-Player Generative Adversarial Network for Synthetic-based Face Recognitioncited by 27
  31. 2023SignDiff: Diffusion Model for American Sign Language Productioncited by 25
  32. 2021MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulationcited by 24
  33. 2022Modulated Contrast for Versatile Image Synthesiscited by 23
  34. 2023Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learningcited by 23
  35. 2021FaceController: Controllable Attribute Editing for Face in the Wildcited by 22
  36. 2021SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfercited by 22
  37. 2022Controllable and Guided Face Synthesis for Unconstrained Face Recognitioncited by 22
  38. 20223DFaceShop: Explicitly Controllable 3D-Aware Portrait Generationcited by 22

50 most cited of 219 All 219 (JSON)