mlsanityData to 7 Oct 2026

Neural Articulated Radiance Field

arXiv 2104.03110 ↗First posted 7 Apr 2021cs.CVcited by 196

Not on the map. Why?

Abstract (arXiv)

We present Neural Articulated Radiance Field (NARF), a novel deformable 3D representation for articulated objects learned from images. While recent advances in 3D implicit representation have made it possible to learn models of complex objects, learning pose-controllable representations of articulated objects remains a challenge, as current methods require 3D shape supervision and are unable to render appearance. In formulating an implicit representation of 3D articulated objects, our method considers only the rigid transformation of the most relevant object part in solving for the radiance field at each 3D location. In this way, the proposed method represents pose-dependent changes without significantly increasing the computational complexity. NARF is fully differentiable and can be trained from images with pose annotations. Moreover, through the use of an autoencoder, it can learn appearance variations over multiple instances of an object class. Experiments show that the proposed method is efficient and can generalize well to novel poses. The code is available for research purposes at https://github.com/nogu-atsu/NARF

Key facts. Cited by 196 papers in the map (data through 7 Oct 2026). Builds on 51 of its 73 references that are in the map. First posted on arXiv 7 Apr 2021.

Builds on

51 of 73 references.

References · 51

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  6. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  7. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  8. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  9. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  10. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  11. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  12. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
38 more
  1. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  2. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  3. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  4. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  5. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  6. 2017Learning from Synthetic Humanscited by 358
  7. 2018Image Generation from Scene Graphscited by 324
  8. 2018Everybody Dance Nowcited by 313
  9. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  10. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  11. 2017Pose Guided Person Image Generationcited by 251
  12. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  13. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  14. 2017Learning a Multi-View Stereo Machinecited by 194
  15. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  16. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  17. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  18. 2017Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistencycited by 177
  19. 2016Panoptic Studio: A Massively Multiview System for Social Interaction Capturecited by 173
  20. 2016View Synthesis by Appearance Flowcited by 172
  21. 2017Deformable GANs for Pose-based Human Image Generationcited by 166
  22. 2019NASA: Neural Articulated Shape Approximationcited by 149
  23. 2018A Variational U-Net for Conditional Appearance and Shape Generationcited by 124
  24. 2015Deep Convolutional Inverse Graphics Networkcited by 121
  25. 2016Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervisioncited by 106
  26. 2017Disentangled Person Image Generationcited by 98
  27. 2018Synthesizing Images of Humans in Unseen Posescited by 96
  28. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  29. 2017Learning to Generate Long-term Future via Hierarchical Predictioncited by 88
  30. 2020STaR: Self-supervised Tracking and Reconstruction of Rigid Objects in Motion with Neural Renderingcited by 76
  31. 2015Multi-view 3D Models from Single Images with a Convolutional Networkcited by 57
  32. 2016SE3-Nets: Learning Rigid Body Motion using Deep Neural Networkscited by 48
  33. 2016Deep Kinematic Pose Regressioncited by 40
  34. 2017A Generative Model of People in Clothingcited by 37
  35. 2014Learning to Generate Chairs, Tables and Cars with Convolutional Networkscited by 26
  36. 2016Single Image 3D Interpreter Networkcited by 19
  37. 2018Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequencescited by 19
  38. 2013Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programscited by 10

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 59; 2023: 71; 2024: 29; 2025: 11; 2026: 8.

196 papers.

Sort:

By area:

  1. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  2. 2021Neural Fields in Visual Computing and Beyondcited by 539
  3. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  4. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  5. 2021Advances in Neural Renderingcited by 365
  6. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
  7. 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 331
  8. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
  9. 2021Neural Head Avatars from Monocular RGB Videoscited by 212
  10. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 199
  11. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  12. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
38 more
  1. 2022TAVA: Template-free Animatable Volumetric Actorscited by 172
  2. 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
  3. 2023GaussianEditor: Editing 3D Gaussians Delicately with Text Instructionscited by 166
  4. 2023HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motioncited by 161
  5. 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
  6. 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Modelscited by 154
  7. 2023DreamEditor: Text-Driven 3D Scene Editing with Neural Fieldscited by 154
  8. 2022Ditto: Building Digital Twins of Articulated Objects from Interactioncited by 152
  9. 2022NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fieldscited by 151
  10. 2022ARAH: Animatable Volume Rendering of Articulated Human SDFscited by 139
  11. 2022InstantAvatar: Learning Avatars from Monocular Video in 60 Secondscited by 138
  12. 2023Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decompositioncited by 134
  13. 2022NeRF-Art: Text-Driven Neural Radiance Fields Stylizationcited by 126
  14. 2023GART: Gaussian Articulated Template Modelscited by 121
  15. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  16. 2022Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generationcited by 119
  17. 2022Structured Local Radiance Fields for Human Avatar Modelingcited by 116
  18. 2023PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objectscited by 115
  19. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
  20. 2022EVA3D: Compositional 3D Human Generation from 2D Image Collectionscited by 111
  21. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 111
  22. 2023ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Renderingcited by 104
  23. 2023DreamHuman: Animatable 3D Avatars from Textcited by 102
  24. 2022Generative Neural Articulated Radiance Fieldscited by 101
  25. 2024Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstructioncited by 100
  26. 2021MoFaNeRF: Morphable Facial Neural Radiance Fieldcited by 94
  27. 2023SHERF: Generalizable Human NeRF from a Single Imagecited by 88
  28. 2023MonoHuman: Animatable Human Neural Field from Monocular Videocited by 85
  29. 2022Deforming Radiance Fields with Cagescited by 78
  30. 2024StyleGaussian: Instant 3D Style Transfer with Gaussian Splattingcited by 78
  31. 2021Learning to Stylize Novel Viewscited by 76
  32. 2022gDNA: Towards Generative Detailed Neural Avatarscited by 72
  33. 2022NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactionscited by 67
  34. 2025ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splattingcited by 67
  35. 2021CoNeRF: Controllable Neural Radiance Fieldscited by 65
  36. 2022Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representationscited by 65
  37. 2022LISA: Learning Implicit Shape and Appearance of Handscited by 63
  38. 2021DOVE: Learning Deformable 3D Objects by Watching Videoscited by 61

50 most cited of 196 All 196 (JSON)