mlsanityData to 7 Oct 2026

3DPortraitGAN: Learning One-Quarter Headshot 3D GANs from a Single-View Portrait Dataset with Diverse Body Poses

arXiv 2307.14770 ↗First posted 27 Jul 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

3D-aware face generators are typically trained on 2D real-life face image datasets that primarily consist of near-frontal face data, and as such, they are unable to construct one-quarter headshot 3D portraits with complete head, neck, and shoulder geometry. Two reasons account for this issue: First, existing facial recognition methods struggle with extracting facial data captured from large camera angles or back views. Second, it is challenging to learn a distribution of 3D portraits covering the one-quarter headshot region from single-view data due to significant geometric deformation caused by diverse body poses. To this end, we first create the dataset 360deg-Portrait-HQ (360degPHQ for short) which consists of high-quality single-view real portraits annotated with a variety of camera parameters (the yaw angles span the entire 360deg range) and body poses. We then propose 3DPortraitGAN, the first 3D-aware one-quarter headshot portrait generator that learns a canonical 3D avatar distribution from the 360degPHQ dataset with body pose self-learning. Our model can generate view-consistent portrait images from all camera angles with a canonical one-quarter headshot 3D representation. Our experiments show that the proposed framework can accurately predict portrait body poses and generate view-consistent, realistic portrait images with complete geometry from all camera angles.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 61 of its 101 references that are in the map. First posted on arXiv 27 Jul 2023.

Builds on

61 of 101 references.

References · 61

  1. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  8. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  9. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  10. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  11. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  12. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
38 more
  1. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  2. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  3. 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 470
  4. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 465
  5. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  6. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  7. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  8. 2021I M Avatar: Implicit Morphable Head Avatars from Videoscited by 230
  9. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  10. 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
  11. 2020FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Predictioncited by 196
  12. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  13. 2020BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Imagescited by 166
  14. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  15. 2022RigNeRF: Fully Controllable Neural 3D Portraitscited by 126
  16. 2018Visual Object Networks: Image Generation with Disentangled 3D Representationcited by 124
  17. 2022EVA3D: Compositional 3D Human Generation from 2D Image Collectionscited by 111
  18. 2023NeRF-DS: Neural Radiance Fields for Dynamic Specular Objectscited by 110
  19. 2020CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotationscited by 109
  20. 2022EpiGRAF: Rethinking training of 3D GANscited by 108
  21. 2021Talk-to-Edit: Fine-Grained Facial Editing via Dialogcited by 102
  22. 2023PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circcited by 93
  23. 2022Multiface: A Dataset for Neural Face Renderingcited by 87
  24. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  25. 2023One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Fieldcited by 68
  26. 2022High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimizationcited by 65
  27. 2021Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenescited by 64
  28. 2023AG3D: Learning to Generate 3D Avatars from 2D Image Collectionscited by 55
  29. 20223D GAN Inversion for Controllable Portrait Image Animationcited by 53
  30. 2022AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatarscited by 46
  31. 20223D GAN Inversion with Pose Optimizationcited by 44
  32. 20223D GAN Inversion with Facial Symmetry Priorcited by 39
  33. 20233DAvatarGAN: Bridging Domains for Personalized Editable Avatarscited by 38
  34. 2022VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relightingcited by 37
  35. 2022Controllable 3D Face Synthesis with Conditional Generative Occupancy Fieldscited by 37
  36. 2022NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fieldscited by 33
  37. 2023LPFF: A Portrait Dataset for Face Generators Across Large Posescited by 22
  38. 2022Everything is There in Latent Space: Attribute Editing and Attribute Style Manipulation by StyleGAN Latent Space Explorationcited by 21

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 4.

8 papers.

  1. 2024Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creationcited by 23
  2. 2024Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Priorcited by 15
  3. 2025Generative Human Geometry Distributioncited by 4
  4. 2025SpinMeRound: Consistent Multi-View Identity Generation Using Diffusion Modelscited by 3
  5. 2025Bringing Your Portrait to 3D Presencecited by 3
  6. 2024NOVA-3D: Non-overlapped Views for 3D Anime Character Reconstructioncited by 2
  7. 2025Human Geometry Distribution for 3D Animation Generationcited by 2
  8. 2024Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusioncited by 1