mlsanityData to 7 Oct 2026

GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians

arXiv 2312.02134 ↗First posted 4 Dec 2023cs.CVcited by 190

Not on the map. Why?

Abstract (arXiv)

We present GaussianAvatar, an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video. We start by introducing animatable 3D Gaussians to explicitly represent humans in various poses and clothing styles. Such an explicit and animatable representation can fuse 3D appearances more efficiently and consistently from 2D observations. Our representation is further augmented with dynamic properties to support pose-dependent appearance modeling, where a dynamic appearance network along with an optimizable feature tensor is designed to learn the motion-to-appearance mapping. Moreover, by leveraging the differentiable motion condition, our method enables a joint optimization of motions and appearances during avatar modeling, which helps to tackle the long-standing issue of inaccurate motion estimation in monocular settings. The efficacy of GaussianAvatar is validated on both the public dataset and our collected dataset, demonstrating its superior performances in terms of appearance quality and rendering efficiency.

Key facts. Cited by 190 papers in the map (data through 7 Oct 2026). Builds on 55 of its 72 references that are in the map. First posted on arXiv 4 Dec 2023.

Builds on

55 of 72 references.

References · 55

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  6. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  7. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
  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. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  11. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  12. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
38 more
  1. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  2. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  3. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  4. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  5. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 238
  6. 2018Video Based Reconstruction of 3D People Modelscited by 237
  7. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  8. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  9. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
  10. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 216
  11. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  12. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 183
  13. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  14. 2022TAVA: Template-free Animatable Volumetric Actorscited by 172
  15. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  16. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  17. 2022SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Videocited by 144
  18. 2022ARAH: Animatable Volume Rendering of Articulated Human SDFscited by 139
  19. 2022InstantAvatar: Learning Avatars from Monocular Video in 60 Secondscited by 138
  20. 2023Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decompositioncited by 134
  21. 2021Real-time Deep Dynamic Characterscited by 133
  22. 2022Structured Local Radiance Fields for Human Avatar Modelingcited by 116
  23. 2020Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstructioncited by 112
  24. 2021Animatable Neural Radiance Fields from Monocular RGB Videoscited by 109
  25. 2018LiveCap: Real-time Human Performance Capture from Monocular Videocited by 93
  26. 2021The Power of Points for Modeling Humans in Clothingcited by 90
  27. 2023MonoHuman: Animatable Human Neural Field from Monocular Videocited by 85
  28. 2023AvatarReX: Real-time Expressive Full-body Avatarscited by 83
  29. 2021Driving-Signal Aware Full-Body Avatarscited by 81
  30. 2022Drivable Volumetric Avatars using Texel-Aligned Featurescited by 62
  31. 2022Learning Implicit Templates for Point-Based Clothed Human Modelingcited by 50
  32. 2023PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modelingcited by 50
  33. 20223D Clothed Human Reconstruction in the Wildcited by 41
  34. 2022DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networkscited by 38
  35. 2023Dynamic Point Fieldscited by 37
  36. 2023Control4D: Efficient 4D Portrait Editing with Textcited by 32
  37. 2021Human Performance Capture from Monocular Video in the Wildcited by 26
  38. 2023NPC: Neural Point Characters from Videocited by 26

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 58; 2025: 83; 2026: 47.

190 papers.

Sort:

By area:

  1. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  2. 2024A Survey on 3D Gaussian Splattingcited by 221
  3. 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 177
  4. 2024Recent Advances in 3D Gaussian Splattingcited by 130
  5. 20243D Gaussian as a New Era: A Surveycited by 102
  6. 2024Generalizable and Animatable Gaussian Head Avatarcited by 95
  7. 2023MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatarcited by 89
  8. 2024Expressive Whole-Body 3D Gaussian Avatarcited by 89
  9. 2024MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereocited by 86
  10. 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 77
  11. 2024Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integrationcited by 66
  12. 2024MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modelingcited by 63
38 more
  1. 2024Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collectionscited by 56
  2. 2024IDOL: Instant Photorealistic 3D Human Creation from a Single Imagecited by 55
  3. 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priorscited by 54
  4. 2024SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstructioncited by 52
  5. 2024CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Modelscited by 52
  6. 2024PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observationscited by 51
  7. 2023SWinGS: Sliding Windows for Dynamic 3D Gaussian Splattingcited by 46
  8. 2024Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Reviewcited by 40
  9. 2024Generalizable Human Gaussians for Sparse View Synthesiscited by 40
  10. 2025Motion Anything: Any to Motion Generationcited by 40
  11. 2025Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Priorcited by 31
  12. 2024HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Priorcited by 30
  13. 2024V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussianscited by 28
  14. 2024LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priorscited by 25
  15. 2024Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Videocited by 25
  16. 2024DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characterscited by 24
  17. 2024Mani-GS: Gaussian Splatting Manipulation with Triangular Meshcited by 22
  18. 2024GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Viewscited by 22
  19. 2025GUAVA: Generalizable Upper Body 3D Gaussian Avatarcited by 22
  20. 2024Expressive Gaussian Human Avatars from Monocular RGB Videocited by 21
  21. 2025HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representationcited by 21
  22. 2024UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modelingcited by 17
  23. 2024Disco4D: Disentangled 4D Human Generation and Animation from a Single Imagecited by 17
  24. 2024Advancing Extended Reality with 3D Gaussian Splatting: Innovations and Prospectscited by 17
  25. 2025MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatarscited by 17
  26. 2024GlossyGS: Inverse Rendering of Glossy Objects with 3D Gaussian Splattingcited by 13
  27. 2025HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restorationcited by 13
  28. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 13
  29. 2025PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Imagecited by 13
  30. 2024GSTalker: Real-time Audio-Driven Talking Face Generation via Deformable Gaussian Splattingcited by 12
  31. 2024Reference-based Controllable Scene Stylization with Gaussian Splattingcited by 12
  32. 2024Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Videocited by 12
  33. 2024DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusioncited by 12
  34. 2024DressRecon: Freeform 4D Human Reconstruction from Monocular Videocited 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. 2025LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Meshcited by 11
  38. 2025TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splattingcited by 11

50 most cited of 190 All 190 (JSON)