mlsanityData to 7 Oct 2026

Expressive Whole-Body 3D Gaussian Avatar

arXiv 2407.21686 ↗First posted 31 Jul 2024cs.CVcited by 89

Not on the map. Why?

Abstract (arXiv)

Facial expression and hand motions are necessary to express our emotions and interact with the world. Nevertheless, most of the 3D human avatars modeled from a casually captured video only support body motions without facial expressions and hand motions.In this work, we present ExAvatar, an expressive whole-body 3D human avatar learned from a short monocular video. We design ExAvatar as a combination of the whole-body parametric mesh model (SMPL-X) and 3D Gaussian Splatting (3DGS). The main challenges are 1) a limited diversity of facial expressions and poses in the video and 2) the absence of 3D observations, such as 3D scans and RGBD images. The limited diversity in the video makes animations with novel facial expressions and poses non-trivial. In addition, the absence of 3D observations could cause significant ambiguity in human parts that are not observed in the video, which can result in noticeable artifacts under novel motions. To address them, we introduce our hybrid representation of the mesh and 3D Gaussians. Our hybrid representation treats each 3D Gaussian as a vertex on the surface with pre-defined connectivity information (i.e., triangle faces) between them following the mesh topology of SMPL-X. It makes our ExAvatar animatable with novel facial expressions by driven by the facial expression space of SMPL-X. In addition, by using connectivity-based regularizers, we significantly reduce artifacts in novel facial expressions and poses.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). Builds on 47 of its 54 references that are in the map. First posted on arXiv 31 Jul 2024.

Builds on

47 of 54 references.

References · 47

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2017Mask R-CNNcited by 7,259
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  7. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  8. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  9. 2018Group Normalizationcited by 1,514
  10. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  11. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  12. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
35 more
  1. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  2. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 611
  3. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  4. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  5. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 475
  6. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  7. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  8. 2023MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Modelcited by 330
  9. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  10. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  11. 2018Video Based Reconstruction of 3D People Modelscited by 237
  12. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 203
  13. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  14. 2023GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussianscited by 190
  15. 2021FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integrationcited by 168
  16. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  17. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  18. 2023SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimationcited by 154
  19. 2023HUGS: Human Gaussian Splatscited by 154
  20. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  21. 2022InstantAvatar: Learning Avatars from Monocular Video in 60 Secondscited by 138
  22. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  23. 2023Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decompositioncited by 134
  24. 2023One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformercited by 128
  25. 2021Animatable Neural Radiance Fields from Monocular RGB Videoscited by 109
  26. 2021imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Posecited by 102
  27. 2020Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimationcited by 81
  28. 2021Driving-Signal Aware Full-Body Avatarscited by 81
  29. 2023X-Avatar: Expressive Human Avatarscited by 66
  30. 2022Drivable Volumetric Avatars using Texel-Aligned Featurescited by 62
  31. 2020DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modelingcited by 49
  32. 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 48
  33. 2024URHand: Universal Relightable Handscited by 17
  34. 2022MonoNHR: Monocular Neural Human Renderercited by 15
  35. 2024Authentic Hand Avatar from a Phone Scan via Universal Hand Modelcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 55; 2026: 32.

89 papers.

Sort:

By area:

  1. 2025LHM: Large Animatable Human Reconstruction Model from a Single Image in Secondscited by 61
  2. 2025Visual Imitation Enables Contextual Humanoid Controlcited by 57
  3. 2025Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Priorcited by 31
  4. 2025GUAVA: Generalizable Upper Body 3D Gaussian Avatarcited by 22
  5. 2025Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidancecited by 16
  6. 2025RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videoscited by 14
  7. 2025PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Imagecited by 13
  8. 2024DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusioncited by 12
  9. 2025RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Imagescited by 12
  10. 2025Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPscited by 12
  11. 2025BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splattingcited by 10
  12. 2025HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformerscited by 9
38 more
  1. 2025MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstructioncited by 8
  2. 2025Disentangled Clothed Avatar Generation with Layered Representationcited by 7
  3. 2025EVA: Expressive Virtual Avatars from Multi-view Videoscited by 7
  4. 2025WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstructioncited by 6
  5. 2025LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3Dcited by 6
  6. 2025Learning to Ball: Composing Policies for Long-Horizon Basketball Movescited by 6
  7. 2025GASPACHO: Gaussian Splatting for Controllable Humans and Objectscited by 5
  8. 2025SignSplat: Rendering Sign Language via Gaussian Splattingcited by 5
  9. 2025Advances in Radiance Field for Dynamic Scene: From Neural Field to Gaussian Fieldcited by 4
  10. 2025SAT: Supervisor Regularization and Animation Augmentation for Two-process Monocular Texture 3D Human Reconstructioncited by 4
  11. 2025AHA! Animating Human Avatars in Diverse Scenes with Gaussian Splattingcited by 4
  12. 2025R3-Avatar: Record and Retrieve Temporal Codebook for Reconstructing Photorealistic Human Avatarscited by 3
  13. 2025Parametric Gaussian Human Model: Generalizable Prior for Efficient and Realistic Human Avatar Modelingcited by 3
  14. 2025MonoCloth: Reconstruction and Animation of Cloth-Decoupled Human Avatars from Monocular Videoscited by 3
  15. 2025PA-HOI: A Physics-Aware Human and Object Interaction Datasetcited by 3
  16. 2025ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstructioncited by 3
  17. 2025SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit 3D Meshescited by 3
  18. 2025Bringing Your Portrait to 3D Presencecited by 3
  19. 2026Zero-Shot Reconstruction of Animatable 3D Avatars with Cloth Dynamics from a Single Imagecited by 3
  20. 2026Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretrainingcited by 3
  21. 2025GaussianMotion: End-to-End Learning of Animatable Gaussian Avatars with Pose Guidance from Textcited by 2
  22. 2025CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splattingcited by 2
  23. 2025SVAD: From Single Image to 3D Avatar via Synthetic Data Generation with Video Diffusion and Data Augmentationcited by 2
  24. 2025Synthetic Human Action Video Data Generation with Pose Transfercited by 2
  25. 2025PHD: Personalized 3D Human Body Fitting with Point Diffusioncited by 2
  26. 2025Generative Modeling of Shape-Dependent Self-Contact Human Posescited by 2
  27. 2025FastAnimate: Towards Learnable Template Construction and Pose Deformation for Fast 3D Human Avatar Animationcited by 2
  28. 2025Relightable and Dynamic Gaussian Avatar Reconstruction from Monocular Videocited by 2
  29. 2026Gaussian Wardrobe: Compositional 3D Gaussian Avatars for Free-Form Virtual Try-Oncited by 2
  30. 2026AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priorscited by 2
  31. 2026High-Fidelity Mobile Avatars with Pruned Local Blendshapescited by 2
  32. 20241st Place Solution to the 8th HANDS Workshop Challenge -- ARCTIC Track: 3DGS-based Bimanual Category-agnostic Interaction Reconstructioncited by 1
  33. 2025Can Pose Transfer Models Generate Realistic Human Motion?cited by 1
  34. 2025Semantics-aware Test-time Adaptation for 3D Human Pose Estimationcited by 1
  35. 2025PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimationcited by 1
  36. 2025HuGeDiff: 3D Human Generation via Diffusion with Gaussian Splattingcited by 1
  37. 2025Learning Efficient and Generalizable Human Representation with Human Gaussian Modelcited by 1
  38. 2025On the Skinning of Gaussian Avatarscited by 1

50 most cited of 89 All 89 (JSON)