mlsanityData to 7 Oct 2026

Structured Local Radiance Fields for Human Avatar Modeling

arXiv 2203.14478 ↗First posted 28 Mar 2022cs.CVcited by 116

Not on the map. Why?

Abstract (arXiv)

It is extremely challenging to create an animatable clothed human avatar from RGB videos, especially for loose clothes due to the difficulties in motion modeling. To address this problem, we introduce a novel representation on the basis of recent neural scene rendering techniques. The core of our representation is a set of structured local radiance fields, which are anchored to the pre-defined nodes sampled on a statistical human body template. These local radiance fields not only leverage the flexibility of implicit representation in shape and appearance modeling, but also factorize cloth deformations into skeleton motions, node residual translations and the dynamic detail variations inside each individual radiance field. To learn our representation from RGB data and facilitate pose generalization, we propose to learn the node translations and the detail variations in a conditional generative latent space. Overall, our method enables automatic construction of animatable human avatars for various types of clothes without the need for scanning subject-specific templates, and can generate realistic images with dynamic details for novel poses. Experiment show that our method outperforms state-of-the-art methods both qualitatively and quantitatively.

Key facts. Cited by 116 papers in the map (data through 7 Oct 2026). Builds on 59 of its 92 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

59 of 92 references.

References · 59

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  2. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  4. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  5. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  7. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  8. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  9. 2020Neural Sparse Voxel Fieldscited by 959
  10. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  11. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  12. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
38 more
  1. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  2. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  3. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  4. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  5. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  6. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  7. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 465
  8. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  9. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  10. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  11. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  12. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  13. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  14. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  15. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  16. 2018Video Based Reconstruction of 3D People Modelscited by 237
  17. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  18. 2021Neural Articulated Radiance Fieldcited by 196
  19. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  20. 2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
  21. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  22. 2020Real-Time High-Resolution Background Mattingcited by 172
  23. 2019Learning to Reconstruct People in Clothing from a Single RGB Cameracited by 168
  24. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
  25. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  26. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  27. 2019NASA: Neural Articulated Shape Approximationcited by 149
  28. 2021Real-time Deep Dynamic Characterscited by 133
  29. 2018Detailed Human Avatars from Monocular Videocited by 109
  30. 2018DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensorcited by 95
  31. 2018LiveCap: Real-time Human Performance Capture from Monocular Videocited by 93
  32. 2021The Power of Points for Modeling Humans in Clothingcited by 90
  33. 2020Deep Implicit Templates for 3D Shape Representationcited by 86
  34. 2021Driving-Signal Aware Full-Body Avatarscited by 81
  35. 2021SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elementscited by 72
  36. 2019Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformationcited by 71
  37. 2018SiCloPe: Silhouette-Based Clothed Peoplecited by 68
  38. 2019Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Imagescited by 67

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 12; 2023: 46; 2024: 27; 2025: 19; 2026: 12.

116 papers.

Sort:

By area:

  1. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  2. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  3. 2023GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussianscited by 190
  4. 2023HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motioncited by 161
  5. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  6. 2023GART: Gaussian Articulated Template Modelscited by 121
  7. 2023Drivable 3D Gaussian Avatarscited by 120
  8. 2023Human Gaussian Splatting: Real-time Rendering of Animatable Avatarscited by 105
  9. 2023DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Renderingcited by 103
  10. 20243D Gaussian as a New Era: A Surveycited by 102
  11. 2023AvatarReX: Real-time Expressive Full-body Avatarscited by 83
  12. 2022KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypointscited by 77
38 more
  1. 2022Learning Neural Parametric Head Modelscited by 73
  2. 2023Learning Neural Volumetric Representations of Dynamic Humans in Minutescited by 70
  3. 2023MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Capturescited by 54
  4. 2024PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observationscited by 51
  5. 2024GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Meshcited by 51
  6. 2022Learning Implicit Templates for Point-Based Clothed Human Modelingcited by 50
  7. 2023PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modelingcited by 50
  8. 2023Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videoscited by 44
  9. 2023Deformable 3D Gaussian Splatting for Animatable Human Avatarscited by 44
  10. 2022Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular Videocited by 37
  11. 2023DELIFFAS: Deformable Light Fields for Fast Avatar Synthesiscited by 36
  12. 2024HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splattingcited by 35
  13. 2024MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videoscited by 34
  14. 2023Control4D: Efficient 4D Portrait Editing with Textcited by 32
  15. 2023Relightable and Animatable Neural Avatar from Sparse-View Videocited by 28
  16. 2023Animatable and Relightable Gaussians for High-fidelity Human Avatar Modelingcited by 27
  17. 2023NPC: Neural Point Characters from Videocited by 26
  18. 2024Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusioncited by 24
  19. 2023Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Streamcited by 23
  20. 2023Drivable Avatar Clothing: Faithful Full-Body Telepresence with Dynamic Clothing Driven by Sparse RGB-D Inputcited by 22
  21. 2024Mani-GS: Gaussian Splatting Manipulation with Triangular Meshcited by 22
  22. 2023CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decompositioncited by 21
  23. 2024CloSe: A 3D Clothing Segmentation Dataset and Modelcited by 21
  24. 2022Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothingcited by 19
  25. 2023Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modelingcited by 19
  26. 2024ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wildcited by 19
  27. 2024OHTA: One-shot Hand Avatar via Data-driven Implicit Priorscited by 18
  28. 2024UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modelingcited by 17
  29. 2024PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modelingcited by 17
  30. 2024StructLDM: Structured Latent Diffusion for 3D Human Generationcited by 17
  31. 2024iHuman: Instant Animatable Digital Humans From Monocular Videoscited by 17
  32. 2023Novel-view Synthesis and Pose Estimation for Hand-Object Interaction from Sparse Viewscited by 16
  33. 2023Animatable 3D Gaussians for High-fidelity Synthesis of Human Motionscited by 15
  34. 2023SlimmeRF: Slimmable Radiance Fieldscited by 15
  35. 2023Implicit Neural Head Synthesis via Controllable Local Deformation Fieldscited by 14
  36. 2024Gaussian Shadow Casting for Neural Characterscited by 14
  37. 2022Dual-Space NeRF: Learning Animatable Avatars and Scene Lighting in Separate Spacescited by 13
  38. 2023HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Posescited by 12

50 most cited of 116 All 116 (JSON)