mlsanityData to 14 Oct 2026

StyleGAN-Human: A Data-Centric Odyssey of Human Generation

arXiv 2204.11823 ↗First posted 25 Apr 2022cs.CV cs.LGcited by 144

Not on the map. Why?

Cited by 40 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Unconditional human image generation is an important task in vision and graphics, which enables various applications in the creative industry. Existing studies in this field mainly focus on "network engineering" such as designing new components and objective functions. This work takes a data-centric perspective and investigates multiple critical aspects in "data engineering", which we believe would complement the current practice. To facilitate a comprehensive study, we collect and annotate a large-scale human image dataset with over 230K samples capturing diverse poses and textures. Equipped with this large dataset, we rigorously investigate three essential factors in data engineering for StyleGAN-based human generation, namely data size, data distribution, and data alignment. Extensive experiments reveal several valuable observations w.r.t. these aspects: 1) Large-scale data, more than 40K images, are needed to train a high-fidelity unconditional human generation model with vanilla StyleGAN. 2) A balanced training set helps improve the generation quality with rare face poses compared to the long-tailed counterpart, whereas simply balancing the clothing texture distribution does not effectively bring an improvement. 3) Human GAN models with body centers for alignment outperform models trained using face centers or pelvis points as alignment anchors. In addition, a model zoo and human editing applications are demonstrated to facilitate future research in the community.

Key facts. Cited by 144 papers in the map (data through 14 Oct 2026). Builds on 86 of its 104 references that are in the map. First posted on arXiv 25 Apr 2022.

Builds on

86 of 104 references.

References · 86

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  8. 2017Improved Training of Wasserstein GANscited by 2,235
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  11. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  12. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
38 more
  1. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  2. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  3. 2016Least Squares Generative Adversarial Networkscited by 1,001
  4. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  5. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  6. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  7. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  8. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  9. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  10. 2020GANSpace: Discovering Interpretable GAN Controlscited by 614
  11. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 544
  12. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
  13. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  14. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  15. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  16. 2020Closed-Form Factorization of Latent Semantics in GANscited by 408
  17. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  18. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 394
  19. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  20. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  21. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  22. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 349
  23. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 332
  24. 2018Everybody Dance Nowcited by 315
  25. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  26. 2017VITON: An Image-based Virtual Try-on Networkcited by 286
  27. 2020StyleRig: Rigging StyleGAN for 3D Control over Portrait Imagescited by 268
  28. 2017Pose Guided Person Image Generationcited by 251
  29. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  30. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  31. 2018Toward Characteristic-Preserving Image-based Virtual Try-On Networkcited by 192
  32. 2017Deformable GANs for Pose-based Human Image Generationcited by 166
  33. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
  34. 2019Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesiscited by 161
  35. 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
  36. 2020TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Stylecited by 149
  37. 2020ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Datacited by 137
  38. 2019Large-scale weakly-supervised pre-training for video action recognitioncited by 130

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 20; 2023: 61; 2024: 28; 2025: 28; 2026: 7.

144 papers.

Sort:

By area:

  1. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  2. 2024Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidancecited by 272
  3. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 219
  4. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  5. 2023StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-Oncited by 175
  6. 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
  7. 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Modelscited by 154
  8. 2023DisCo: Disentangled Control for Realistic Human Dance Generationcited by 142
  9. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Samplingcited by 129
  10. 2023GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learningcited by 120
  11. 2023MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusioncited by 117
  12. 2022EVA3D: Compositional 3D Human Generation from 2D Image Collectionscited by 111
38 more
  1. 2023TADA! Text to Animatable Digital Avatarscited by 110
  2. 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
  3. 2023HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusioncited by 68
  4. 2024Advances in 3D Generation: A Surveycited by 63
  5. 2023Gaussian Shell Maps for Efficient 3D Human Generationcited by 61
  6. 2022AvatarGen: A 3D Generative Model for Animatable Human Avatarscited by 59
  7. 2022AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatarscited by 55
  8. 2023AG3D: Learning to Generate 3D Avatars from 2D Image Collectionscited by 55
  9. 2023Learning Locally Editable Virtual Humanscited by 54
  10. 2023MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Capturescited by 54
  11. 2023Text2Performer: Text-Driven Human Video Generationcited by 53
  12. 2024Diffusion Model-Based Video Editing: A Surveycited by 44
  13. 2023PoseFix: Correcting 3D Human Poses with Natural Languagecited by 40
  14. 2023Towards Garment Sewing Pattern Reconstruction from a Single Imagecited by 34
  15. 2023Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Imagescited by 34
  16. 2023PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generationcited by 34
  17. 2022HumanGen: Generating Human Radiance Fields with Explicit Priorscited by 33
  18. 2022Text2Human: Text-Driven Controllable Human Image Generationcited by 31
  19. 2023SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Imagecited by 30
  20. 2024CosmicMan: A Text-to-Image Foundation Model for Humanscited by 30
  21. 2023GETAvatar: Generative Textured Meshes for Animatable Human Avatarscited by 27
  22. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  23. 2022Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversioncited by 24
  24. 2024CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Modelscited by 24
  25. 2024MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinementcited by 24
  26. 2023HumanLiff: Layer-wise 3D Human Generation with Diffusion Modelcited by 23
  27. 2023HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusioncited by 23
  28. 2024ChatGarment: Garment Estimation, Generation and Editing via Large Language Modelscited by 23
  29. 2024Expressive Gaussian Human Avatars from Monocular RGB Videocited by 21
  30. 2023Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Modelscited by 20
  31. 2023Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priorscited by 19
  32. 2023Image-Based Virtual Try-On: A Surveycited by 19
  33. 2023RaBit: Parametric Modeling of 3D Biped Cartoon Characters with a Topological-consistent Datasetcited by 18
  34. 20223DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mappingcited by 17
  35. 2023XAGen: 3D Expressive Human Avatars Generationcited by 17
  36. 2024StructLDM: Structured Latent Diffusion for 3D Human Generationcited by 17
  37. 2022A Survey on Deep Generative 3D-aware Image Synthesiscited by 16
  38. 2023AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Collectionscited by 16

50 most cited of 144 All 144 (JSON)