mlsanityData to 14 Oct 2026

NeuMan: Neural Human Radiance Field from a Single Video

arXiv 2203.12575 ↗First posted 23 Mar 2022cs.CVcited by 244

Not on the map. Why?

Abstract (arXiv)

Photorealistic rendering and reposing of humans is important for enabling augmented reality experiences. We propose a novel framework to reconstruct the human and the scene that can be rendered with novel human poses and views from just a single in-the-wild video. Given a video captured by a moving camera, we train two NeRF models: a human NeRF model and a scene NeRF model. To train these models, we rely on existing methods to estimate the rough geometry of the human and the scene. Those rough geometry estimates allow us to create a warping field from the observation space to the canonical pose-independent space, where we train the human model in. Our method is able to learn subject specific details, including cloth wrinkles and accessories, from just a 10 seconds video clip, and to provide high quality renderings of the human under novel poses, from novel views, together with the background.

Key facts. Cited by 244 papers in the map (data through 14 Oct 2026). Builds on 33 of its 54 references that are in the map. First posted on arXiv 23 Mar 2022.

Builds on

33 of 54 references.

References · 33

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2017Mask R-CNNcited by 7,277
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  4. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  5. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  6. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  7. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  8. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  9. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  10. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  11. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
  12. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 532
21 more
  1. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  2. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  3. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  4. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  5. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  6. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  7. 2021Learning Object-Compositional Neural Radiance Field for Editable Scene Renderingcited by 228
  8. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 218
  9. 2019Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesiscited by 161
  10. 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
  11. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  12. 2017Disentangled Person Image Generationcited by 98
  13. 2018Synthesizing Images of Humans in Unseen Posescited by 97
  14. 2020Object-Centric Neural Scene Renderingcited by 90
  15. 2021LOLNeRF: Learn from One Lookcited by 84
  16. 2018Dense Pose Transfercited by 83
  17. 2021Neural Re-Rendering of Humans from a Single Imagecited by 59
  18. 2020Neural Volume Rendering: NeRF And Beyondcited by 44
  19. 2020Vid2Actor: Free-viewpoint Animatable Person Synthesis from Video in the Wildcited by 35
  20. 2019Learning Multi-Human Optical Flowcited by 26
  21. 2021Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistencycited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 13; 2023: 80; 2024: 66; 2025: 47; 2026: 38.

244 papers.

Sort:

By area:

  1. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  2. 2023GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussianscited by 191
  3. 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
  4. 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
  5. 2024OmniRe: Omni Urban Scene Reconstructioncited by 161
  6. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 158
  7. 2023HUGS: Human Gaussian Splatscited by 154
  8. 2022InstantAvatar: Learning Avatars from Monocular Video in 60 Secondscited by 138
  9. 2023Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decompositioncited by 134
  10. 2023GART: Gaussian Articulated Template Modelscited by 121
  11. 2023Drivable 3D Gaussian Avatarscited by 120
  12. 2022EVA3D: Compositional 3D Human Generation from 2D Image Collectionscited by 111
38 more
  1. 20243D Gaussian as a New Era: A Surveycited by 104
  2. 2023DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Renderingcited by 103
  3. 2022Generative Neural Articulated Radiance Fieldscited by 101
  4. 2024Expressive Whole-Body 3D Gaussian Avatarcited by 89
  5. 2023SHERF: Generalizable Human NeRF from a Single Imagecited by 88
  6. 2023MonoHuman: Animatable Human Neural Field from Monocular Videocited by 85
  7. 2023AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Controlcited by 84
  8. 2023DreamWaltz: Make a Scene with Complex 3D Animatable Avatarscited by 82
  9. 2023SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstructioncited by 77
  10. 2024Fully Explicit Dynamic Gaussian Splattingcited by 76
  11. 2023SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusioncited by 72
  12. 2024MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modelingcited by 64
  13. 2023Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstructioncited by 61
  14. 2022Fast-SNARF: A Fast Deformer for Articulated Neural Fieldscited by 55
  15. 2023AG3D: Learning to Generate 3D Avatars from 2D Image Collectionscited by 55
  16. 2023NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenescited by 53
  17. 2024GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Meshcited by 51
  18. 2023PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modelingcited by 50
  19. 2024REACTO: Reconstructing Articulated Objects from a Single Videocited by 45
  20. 2023Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videoscited by 44
  21. 2023Deformable 3D Gaussian Splatting for Animatable Human Avatarscited by 44
  22. 2024SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Videocited by 44
  23. 2022Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular Videocited by 37
  24. 2023DELIFFAS: Deformable Light Fields for Fast Avatar Synthesiscited by 36
  25. 2023SplatArmor: Articulated Gaussian splatting for animatable humans from monocular RGB videoscited by 35
  26. 2024MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videoscited by 34
  27. 2023HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Videocited by 33
  28. 2023Human101: Training 100+FPS Human Gaussians in 100s from 1 Viewcited by 32
  29. 2025Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Priorcited by 31
  30. 2022State of the Art in Dense Monocular Non-Rigid 3D Reconstructioncited by 30
  31. 2023SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Imagecited by 30
  32. 2022Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categoriescited by 29
  33. 2023REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videoscited by 29
  34. 2023DINAR: Diffusion Inpainting of Neural Textures for One-Shot Human Avatarscited by 28
  35. 2023Relightable and Animatable Neural Avatar from Sparse-View Videocited by 28
  36. 20233D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimationcited by 28
  37. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  38. 2023HandNeRF: Neural Radiance Fields for Animatable Interacting Handscited by 27

50 most cited of 244 All 244 (JSON)