mlsanityData to 14 Oct 2026

GauHuman: Articulated Gaussian Splatting from Monocular Human Videos

arXiv 2312.02973 ↗First posted 5 Dec 2023cs.CVcited by 168

Not on the map. Why?

Abstract (arXiv)

We present, GauHuman, a 3D human model with Gaussian Splatting for both fast training (1 ~ 2 minutes) and real-time rendering (up to 189 FPS), compared with existing NeRF-based implicit representation modelling frameworks demanding hours of training and seconds of rendering per frame. Specifically, GauHuman encodes Gaussian Splatting in the canonical space and transforms 3D Gaussians from canonical space to posed space with linear blend skinning (LBS), in which effective pose and LBS refinement modules are designed to learn fine details of 3D humans under negligible computational cost. Moreover, to enable fast optimization of GauHuman, we initialize and prune 3D Gaussians with 3D human prior, while splitting/cloning via KL divergence guidance, along with a novel merge operation for further speeding up. Extensive experiments on ZJU_Mocap and MonoCap datasets demonstrate that GauHuman achieves state-of-the-art performance quantitatively and qualitatively with fast training and real-time rendering speed. Notably, without sacrificing rendering quality, GauHuman can fast model the 3D human performer with ~13k 3D Gaussians.

Key facts. Cited by 168 papers in the map (data through 14 Oct 2026). Builds on 100 of its 146 references that are in the map. First posted on arXiv 5 Dec 2023.

Builds on

100 of 146 references.

References · 100

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2023Segment Anythingcited by 8,234
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  6. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  7. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  8. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  9. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  10. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  11. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  12. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
38 more
  1. 2020Neural Sparse Voxel Fieldscited by 959
  2. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  3. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  4. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  5. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  6. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  7. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  8. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  9. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  10. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  11. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  12. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  13. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  14. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 511
  15. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  16. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  17. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 476
  18. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  19. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  20. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 405
  21. 2021Advances in Neural Renderingcited by 365
  22. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  23. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  24. 2019Neural Point-Based Graphicscited by 327
  25. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  26. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  27. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  28. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 239
  29. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  30. 2020Free View Synthesiscited by 231
  31. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
  32. 2021Neural Articulated Radiance Fieldcited by 196
  33. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 196
  34. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  35. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  36. 2021Point-Based Neural Rendering with Per-View Optimizationcited by 190
  37. 2015DeepStereo: Learning to Predict New Views from the World's Imagerycited by 185
  38. 2020GRF: Learning a General Radiance Field for 3D Representation and Renderingcited by 183

50 most cited of 100 All 100 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 57; 2025: 71; 2026: 38.

168 papers.

Sort:

By area:

  1. 2024A Survey on 3D Gaussian Splattingcited by 224
  2. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  3. 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 179
  4. 2024OmniRe: Omni Urban Scene Reconstructioncited by 161
  5. 2024Recent Advances in 3D Gaussian Splattingcited by 131
  6. 20243D Gaussian as a New Era: A Surveycited by 104
  7. 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 78
  8. 2024Fully Explicit Dynamic Gaussian Splattingcited by 76
  9. 2025LHM: Large Animatable Human Reconstruction Model from a Single Image in Secondscited by 61
  10. 2024Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesiscited by 58
  11. 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priorscited by 54
  12. 2024SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstructioncited by 52
38 more
  1. 2024GGHead: Fast and Generalizable 3D Gaussian Headscited by 51
  2. 2024Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Reviewcited by 41
  3. 2024HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splattingcited by 35
  4. 2024MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videoscited by 34
  5. 2024Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstructioncited by 32
  6. 2024HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Priorcited by 31
  7. 2025Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Priorcited by 31
  8. 2024Generalizable Human Gaussians from Single-View Imagecited by 29
  9. 2024LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priorscited by 25
  10. 2024ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generationcited by 25
  11. 2024GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videoscited by 22
  12. 2024LayGA: Layered Gaussian Avatars for Animatable Clothing Transfercited by 22
  13. 2024Beyond Gaussians: Fast and High-Fidelity 3D Splatting with Linear Kernelscited by 22
  14. 2025Relightable Full-Body Gaussian Codec Avatarscited by 22
  15. 2025GUAVA: Generalizable Upper Body 3D Gaussian Avatarcited by 22
  16. 2024GauU-Scene V2: Assessing the Reliability of Image-Based Metrics with Expansive Lidar Image Dataset Using 3DGS and NeRFcited by 21
  17. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  18. 2024UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modelingcited by 17
  19. 2024GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splattingcited by 17
  20. 2024Disco4D: Disentangled 4D Human Generation and Animation from a Single Imagecited by 17
  21. 2025Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Modelscited by 17
  22. 2024GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splattingcited by 15
  23. 2024A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generationcited by 13
  24. 2024GlossyGS: Inverse Rendering of Glossy Objects with 3D Gaussian Splattingcited by 13
  25. 2025Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactionscited by 13
  26. 2025Articulated Kinematics Distillation from Video Diffusion Modelscited by 13
  27. 2025HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restorationcited by 13
  28. 2025InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsingcited by 13
  29. 2024GSTalker: Real-time Audio-Driven Talking Face Generation via Deformable Gaussian Splattingcited by 12
  30. 2024Surfel-based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction from Monocular Videocited by 12
  31. 2025RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Imagescited by 12
  32. 2025Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPscited by 12
  33. 2024GST: Precise 3D Human Body from a Single Image with Gaussian Splatting Transformerscited by 11
  34. 2024SqueezeMe: Mobile-Ready Distillation of Gaussian Full-Body Avatarscited by 11
  35. 2025TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splattingcited by 11
  36. 2024DEGAS: Detailed Expressions on Full-Body Gaussian Avatarscited by 10
  37. 2024ToMiE: Towards Explicit Exoskeleton for the Reconstruction of Complicated 3D Human Avatarscited by 10
  38. 2024MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstructioncited by 10

50 most cited of 168 All 168 (JSON)