mlsanityData to 7 Oct 2026

Lifting 2D StyleGAN for 3D-Aware Face Generation

arXiv 2011.13126 ↗First posted 26 Nov 2020cs.CVcited by 64

Not on the map. Why?

Abstract (arXiv)

We propose a framework, called LiftedGAN, that disentangles and lifts a pre-trained StyleGAN2 for 3D-aware face generation. Our model is "3D-aware" in the sense that it is able to (1) disentangle the latent space of StyleGAN2 into texture, shape, viewpoint, lighting and (2) generate 3D components for rendering synthetic images. Unlike most previous methods, our method is completely self-supervised, i.e. it neither requires any manual annotation nor 3DMM model for training. Instead, it learns to generate images as well as their 3D components by distilling the prior knowledge in StyleGAN2 with a differentiable renderer. The proposed model is able to output both the 3D shape and texture, allowing explicit pose and lighting control over generated images. Qualitative and quantitative results show the superiority of our approach over existing methods on 3D-controllable GANs in content controllability while generating realistic high quality images.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 23; 2023: 23; 2024: 7; 2025: 4; 2026: 2.

64 papers.

Sort:

By area:

  1. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  2. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  3. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  4. 2022EpiGRAF: Rethinking training of 3D GANscited by 108
  5. 2023PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circcited by 93
  6. 2022GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifoldscited by 73
  7. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  8. 2021GAN-Supervised Dense Visual Alignmentcited by 61
  9. 2022Generative Multiplane Images: Making a 2D GAN 3D-Awarecited by 57
  10. 2023Learning Locally Editable Virtual Humanscited by 54
  11. 20223D GAN Inversion for Controllable Portrait Image Animationcited by 53
  12. 2023TriPlaneNet: An Encoder for EG3D Inversioncited by 41
38 more
  1. 20233DAvatarGAN: Bridging Domains for Personalized Editable Avatarscited by 38
  2. 2022Controllable 3D Face Synthesis with Conditional Generative Occupancy Fieldscited by 37
  3. 2023Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encodingcited by 35
  4. 2023OmniAvatar: Geometry-Guided Controllable 3D Head Synthesiscited by 34
  5. 2022DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Modelcited by 32
  6. 2023VQ3D: Learning a 3D-Aware Generative Model on ImageNetcited by 32
  7. 2022One-Shot Adaptation of GAN in Just One CLIPcited by 31
  8. 2024SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representationcited by 30
  9. 2022PV3D: A 3D Generative Model for Portrait Video Generationcited by 23
  10. 20223DFaceShop: Explicitly Controllable 3D-Aware Portrait Generationcited by 22
  11. 2023FaceLit: Neural 3D Relightable Facescited by 20
  12. 2023Towards Realistic Generative 3D Face Modelscited by 20
  13. 2023CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Imagescited by 19
  14. 2023Mimic3D: Thriving 3D-Aware GANs via 3D-to-2D Imitationcited by 18
  15. 20223D-FM GAN: Towards 3D-Controllable Face Manipulationcited by 17
  16. 2023XAGen: 3D Expressive Human Avatars Generationcited by 17
  17. 2022A Survey on Deep Generative 3D-aware Image Synthesiscited by 16
  18. 2023AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Collectionscited by 16
  19. 2023Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Fieldcited by 15
  20. 2023LumiGAN: Unconditional Generation of Relightable 3D Human Facescited by 14
  21. 2024Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networkscited by 14
  22. 2023NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANscited by 12
  23. 20222D GANs Meet Unsupervised Single-view 3D Reconstructioncited by 11
  24. 2022Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesiscited by 11
  25. 2022Controllable Evaluation and Generation of Physical Adversarial Patch on Face Recognitioncited by 8
  26. 2022Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generationcited by 8
  27. 2022Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis from Monocular Imagecited by 7
  28. 2023Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformerscited by 7
  29. 2025PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Imagecited by 7
  30. 2021FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifoldcited by 6
  31. 2022Multi-NeuS: 3D Head Portraits from Single Image with Neural Implicit Functionscited by 6
  32. 2025HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesiscited by 6
  33. 2024G3DR: Generative 3D Reconstruction in ImageNetcited by 5
  34. 2024Diversity-aware Channel Pruning for StyleGAN Compressioncited by 5
  35. 2024A Survey on Physical Adversarial Attacks against Face Recognition Systemscited by 4
  36. 20223D-GIF: 3D-Controllable Object Generation via Implicit Factorized Representationscited by 3
  37. 2023NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutionscited by 3
  38. 2021Causal Representation Learning for Context-Aware Face Transfercited by 2

50 most cited of 64 All 64 (JSON)