mlsanityData to 7 Oct 2026

HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs

arXiv 2112.02789 ↗First posted 6 Dec 2021cs.CV cs.GRcited by 112

Not on the map. Why?

Abstract (arXiv)

Recent neural human representations can produce high-quality multi-view rendering but require using dense multi-view inputs and costly training. They are hence largely limited to static models as training each frame is infeasible. We present HumanNeRF - a generalizable neural representation - for high-fidelity free-view synthesis of dynamic humans. Analogous to how IBRNet assists NeRF by avoiding per-scene training, HumanNeRF employs an aggregated pixel-alignment feature across multi-view inputs along with a pose embedded non-rigid deformation field for tackling dynamic motions. The raw HumanNeRF can already produce reasonable rendering on sparse video inputs of unseen subjects and camera settings. To further improve the rendering quality, we augment our solution with an appearance blending module for combining the benefits of both neural volumetric rendering and neural texture blending. Extensive experiments on various multi-view dynamic human datasets demonstrate the generalizability and effectiveness of our approach in synthesizing photo-realistic free-view humans under challenging motions and with very sparse camera view inputs.

Key facts. Cited by 112 papers in the map (data through 7 Oct 2026). Builds on 31 of its 60 references that are in the map. First posted on arXiv 6 Dec 2021.

Builds on

31 of 60 references.

References · 31

  1. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  2. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  3. 2020Neural Sparse Voxel Fieldscited by 959
  4. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  5. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  6. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  7. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  8. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  9. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  10. 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 470
  11. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  12. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
19 more
  1. 2019Neural Point-Based Graphicscited by 326
  2. 2020State of the Art on Neural Renderingcited by 276
  3. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  4. 2019Deferred Neural Rendering: Image Synthesis using Neural Texturescited by 253
  5. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  6. 2020Stable View Synthesiscited by 165
  7. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  8. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  9. 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
  10. 2021Real-time Deep Dynamic Characterscited by 133
  11. 2016Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervisioncited by 106
  12. 2021Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Controlcited by 106
  13. 2021Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothingcited by 102
  14. 2018DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensorcited by 95
  15. 2019EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Cameracited by 65
  16. 2021NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Camerascited by 40
  17. 2021SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videoscited by 40
  18. 2021RobustFusion: Robust Volumetric Performance Reconstruction under Human-object Interactions from Monocular RGBD Streamcited by 26
  19. 2021iButter: Neural Interactive Bullet Time Generator for Human Free-viewpoint Renderingcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 15; 2023: 46; 2024: 20; 2025: 20; 2026: 11.

112 papers.

Sort:

By area:

  1. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  2. 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
  3. 2022Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-timecited by 164
  4. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  5. 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videoscited by 156
  6. 2023DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splattingcited by 124
  7. 2023DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Renderingcited by 103
  8. 2023DreamHuman: Animatable 3D Avatars from Textcited by 102
  9. 2023Neural Residual Radiance Fields for Streamably Free-Viewpoint Videoscited by 77
  10. 2022DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priorscited by 70
  11. 2023HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splattingcited by 68
  12. 2022NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactionscited by 67
38 more
  1. 2022Human Performance Modeling and Rendering via Neural Animated Meshcited by 64
  2. 2023Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstructioncited by 60
  3. 2023AG3D: Learning to Generate 3D Avatars from 2D Image Collectionscited by 55
  4. 2023SWinGS: Sliding Windows for Dynamic 3D Gaussian Splattingcited by 46
  5. 2023Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstructioncited by 43
  6. 2024Generalizable Human Gaussians for Sparse View Synthesiscited by 40
  7. 2022One-shot Implicit Animatable Avatars with Model-based Priorscited by 38
  8. 2024Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfelscited by 38
  9. 2022Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular Videocited by 37
  10. 2022HumanGen: Generating Human Radiance Fields with Explicit Priorscited by 33
  11. 2025Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Priorcited by 31
  12. 2024Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videoscited by 30
  13. 2023REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videoscited by 29
  14. 2023HandNeRF: Neural Radiance Fields for Animatable Interacting Handscited by 27
  15. 2023BeyondPixels: A Comprehensive Review of the Evolution of Neural Radiance Fieldscited by 27
  16. 2024LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitivescited by 25
  17. 2022SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fieldscited by 23
  18. 2023Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Streamcited by 23
  19. 2023Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Inputcited by 22
  20. 2024GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Viewscited by 22
  21. 2023ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFscited by 21
  22. 2023NSF: Neural Surface Fields for Human Modeling from Monocular Depthcited by 21
  23. 2024Expressive Gaussian Human Avatars from Monocular RGB Videocited by 21
  24. 2023Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modelingcited by 19
  25. 2025GAS: Generative Avatar Synthesis from a Single Imagecited by 19
  26. 2023TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Renderingcited by 18
  27. 2024OHTA: One-shot Hand Avatar via Data-driven Implicit Priorscited by 18
  28. 2024PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modelingcited by 17
  29. 2023Sync-NeRF: Generalizing Dynamic NeRFs to Unsynchronized Videoscited by 16
  30. 2023Template-free Articulated Neural Point Clouds for Reposable View Synthesiscited by 15
  31. 2023Animatable 3D Gaussians for High-fidelity Synthesis of Human Motionscited by 15
  32. 2023SlimmeRF: Slimmable Radiance Fieldscited by 15
  33. 2025InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsingcited by 13
  34. 2023HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Posescited by 12
  35. 2025RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Imagescited by 12
  36. 2025SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assetscited by 12
  37. 2022Relightable Neural Human Assets from Multi-view Gradient Illuminationscited by 11
  38. 2024MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Renderingcited by 11

50 most cited of 112 All 112 (JSON)