mlsanityData to 7 Oct 2026

HumanGen: Generating Human Radiance Fields with Explicit Priors

arXiv 2212.05321 ↗First posted 10 Dec 2022cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Recent years have witnessed the tremendous progress of 3D GANs for generating view-consistent radiance fields with photo-realism. Yet, high-quality generation of human radiance fields remains challenging, partially due to the limited human-related priors adopted in existing methods. We present HumanGen, a novel 3D human generation scheme with detailed geometry and 360circ realistic free-view rendering. It explicitly marries the 3D human generation with various priors from the 2D generator and 3D reconstructor of humans through the design of "anchor image". We introduce a hybrid feature representation using the anchor image to bridge the latent space of HumanGen with the existing 2D generator. We then adopt a pronged design to disentangle the generation of geometry and appearance. With the aid of the anchor image, we adapt a 3D reconstructor for fine-grained details synthesis and propose a two-stage blending scheme to boost appearance generation. Extensive experiments demonstrate our effectiveness for state-of-the-art 3D human generation regarding geometry details, texture quality, and free-view performance. Notably, HumanGen can also incorporate various off-the-shelf 2D latent editing methods, seamlessly lifting them into 3D.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 83 of its 95 references that are in the map. First posted on arXiv 10 Dec 2022.

Builds on

83 of 95 references.

References · 83

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  7. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  8. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  9. 2018Demystifying MMD GANscited by 1,268
  10. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  11. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  12. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
38 more
  1. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  2. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  3. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  4. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  5. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  6. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  7. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  8. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  9. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  10. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  11. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  12. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  13. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  14. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  15. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  16. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  17. 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
  18. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  19. 2018Video-to-Video Synthesiscited by 388
  20. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  21. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 331
  22. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  23. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  24. 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
  25. 2021GRAM: Generative Radiance Manifolds for 3D-Aware Image Generationcited by 216
  26. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  27. 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 208
  28. 2021Neural Articulated Radiance Fieldcited by 196
  29. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  30. 2022TAVA: Template-free Animatable Volumetric Actorscited by 172
  31. 2018Escaping Plato's Cave: 3D Shape From Adversarial Renderingcited by 170
  32. 2020BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Imagescited by 166
  33. 2022Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-timecited by 164
  34. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  35. 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
  36. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  37. 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
  38. 2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 143

50 most cited of 83 All 83 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 16; 2024: 8; 2025: 6; 2026: 1.

33 papers.

Sort:

By area:

  1. 2024Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidancecited by 271
  2. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  3. 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Modelscited by 154
  4. 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
  5. 2024Advances in 3D Generation: A Surveycited by 62
  6. 2023Gaussian Shell Maps for Efficient 3D Human Generationcited by 61
  7. 2023AG3D: Learning to Generate 3D Avatars from 2D Image Collectionscited by 55
  8. 2023MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Capturescited by 54
  9. 2023Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstructioncited by 42
  10. 2023AvatarBooth: High-Quality and Customizable 3D Human Avatar Generationcited by 37
  11. 2023PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generationcited by 33
  12. 2023Get3DHuman: Lifting StyleGAN-Human into a 3D Generative Model using Pixel-aligned Reconstruction Priorscited by 19
21 more
  1. 2023Template-free Articulated Neural Point Clouds for Reposable View Synthesiscited by 15
  2. 2024En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Datacited by 14
  3. 2023Efficient 3D Articulated Human Generation with Layered Surface Volumescited by 13
  4. 2024A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generationcited by 13
  5. 2024HPC: Hierarchical Progressive Coding Framework for Volumetric Videocited by 13
  6. 2025Neural Radiance Fields for the Real World: A Surveycited by 12
  7. 2022Human Image Generation: A Comprehensive Surveycited by 11
  8. 2025MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitizationcited by 9
  9. 2023AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexingcited by 8
  10. 2024NeRFFaceSpeech: One-shot Audio-driven 3D Talking Head Synthesis via Generative Priorcited by 8
  11. 2023SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshescited by 7
  12. 2025HumanGif: Single-View Human Diffusion with Generative Priorcited by 7
  13. 2023Articulated 3D Head Avatar Generation using Text-to-Image Diffusion Modelscited by 6
  14. 2023Joint2Human: High-quality 3D Human Generation via Compact Spherical Embedding of 3D Jointscited by 6
  15. 2023MVHuman: Tailoring 2D Diffusion with Multi-view Sampling For Realistic 3D Human Generationcited by 6
  16. 2024StdGEN: Semantic-Decomposed 3D Character Generation from Single Imagescited by 5
  17. 2025Generative Human Geometry Distributioncited by 4
  18. 2024SemanticHuman-HD: High-Resolution Semantic Disentangled 3D Human Generationcited by 3
  19. 2025EverybodyDance: Bipartite Graph-Based Identity Correspondence for Multi-Character Animationcited by 3
  20. 2025SVAD: From Single Image to 3D Avatar via Synthetic Data Generation with Video Diffusion and Data Augmentationcited by 2
  21. 2026StdGEN++: A Comprehensive System for Semantic-Decomposed 3D Character Generationcited by 1