mlsanityData to 14 Oct 2026

Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors

arXiv 2105.01859 ↗First posted 5 May 2021cs.CVcited by 246

Not on the map. Why?

Cited by 41 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Human volumetric capture is a long-standing topic in computer vision and computer graphics. Although high-quality results can be achieved using sophisticated off-line systems, real-time human volumetric capture of complex scenarios, especially using light-weight setups, remains challenging. In this paper, we propose a human volumetric capture method that combines temporal volumetric fusion and deep implicit functions. To achieve high-quality and temporal-continuous reconstruction, we propose dynamic sliding fusion to fuse neighboring depth observations together with topology consistency. Moreover, for detailed and complete surface generation, we propose detail-preserving deep implicit functions for RGBD input which can not only preserve the geometric details on the depth inputs but also generate more plausible texturing results. Results and experiments show that our method outperforms existing methods in terms of view sparsity, generalization capacity, reconstruction quality, and run-time efficiency.

Key facts. Cited by 246 papers in the map (data through 14 Oct 2026). Builds on 26 of its 63 references that are in the map. First posted on arXiv 5 May 2021.

Builds on

26 of 63 references.

References · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  6. 2020Convolutional Occupancy Networkscited by 761
  7. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  8. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  9. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  10. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  11. 2019DeepHuman: 3D Human Reconstruction from a Single Imagecited by 182
  12. 2019Tex2Shape: Detailed Full Human Body Geometry From a Single Imagecited by 166
14 more
  1. 2020DeepCap: Monocular Human Performance Capture Using Weak Supervisioncited by 162
  2. 2020Combining Implicit Function Learning and Parametric Models for 3D Human Reconstructioncited by 133
  3. 2018DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensorcited by 95
  4. 2018LiveCap: Real-time Human Performance Capture from Monocular Videocited by 93
  5. 2019DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Datacited by 77
  6. 2020Monocular Real-Time Volumetric Performance Capturecited by 74
  7. 2019Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformationcited by 71
  8. 2018SiCloPe: Silhouette-Based Clothed Peoplecited by 68
  9. 2019Moulding Humans: Non-parametric 3D Human Shape Estimation from Single Imagescited by 67
  10. 2017MonoPerfCap: Human Performance Capture from Monocular Videocited by 63
  11. 2020Robust 3D Self-portraits in Secondscited by 30
  12. 2020NormalGAN: Learning Detailed 3D Human from a Single RGB-D Imagecited by 24
  13. 2016Temporally coherent 4D reconstruction of complex dynamic scenescited by 21
  14. 2018ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Cameracited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 27; 2023: 45; 2024: 71; 2025: 64; 2026: 34.

246 papers.

Sort:

By area:

  1. 2021Neural Fields in Visual Computing and Beyondcited by 540
  2. 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 249
  3. 2024Sapiens: Foundation for Human Vision Modelscited by 229
  4. 2024A Survey on 3D Gaussian Splattingcited by 224
  5. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  6. 2024Taming 3DGS: High-Quality Radiance Fields with Limited Resourcescited by 204
  7. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  8. 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
  9. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 117
  10. 2022Structured Local Radiance Fields for Human Avatar Modelingcited by 116
  11. 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
  12. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
38 more
  1. 2023DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Renderingcited by 103
  2. 2022FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Datasetcited by 98
  3. 20234K4D: Real-Time 4D View Synthesis at 4K Resolutioncited by 91
  4. 2023SHERF: Generalizable Human NeRF from a Single Imagecited by 88
  5. 2023HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generationcited by 88
  6. 2023SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstructioncited by 77
  7. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 74
  8. 2023SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusioncited by 72
  9. 2023High-fidelity 3D Human Digitization from Single 2K Resolution Imagescited by 70
  10. 2023HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splattingcited by 70
  11. 2022Human Performance Modeling and Rendering via Neural Animated Meshcited by 64
  12. 2022Drivable Volumetric Avatars using Texel-Aligned Featurescited by 62
  13. 2024Human4DiT: 360-degree Human Video Generation with 4D Diffusion Transformercited by 61
  14. 2023DFormer: Rethinking RGBD Representation Learning for Semantic Segmentationcited by 60
  15. 2022A Survey of Non-Rigid 3D Registrationcited by 59
  16. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 59
  17. 2024IDOL: Instant Photorealistic 3D Human Creation from a Single Imagecited by 55
  18. 2023Learning Locally Editable Virtual Humanscited by 54
  19. 2023MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Capturescited by 54
  20. 20244D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotationscited by 54
  21. 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priorscited by 54
  22. 2021DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Renderingcited by 52
  23. 2022NeuralHOFusion: Neural Volumetric Rendering under Human-object Interactionscited by 44
  24. 2024Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Modelscited by 44
  25. 2022UV Volumes for Real-time Rendering of Editable Free-view Human Performancecited by 43
  26. 2022DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Camerascited by 43
  27. 2023Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstructioncited by 42
  28. 2023Single-Image 3D Human Digitization with Shape-Guided Diffusioncited by 42
  29. 2024Generalizable Human Gaussians for Sparse View Synthesiscited by 40
  30. 2023High-Fidelity Clothed Avatar Reconstruction from a Single Imagecited by 38
  31. 2021Neural Free-Viewpoint Performance Rendering under Complex Human-object Interactionscited by 37
  32. 2024AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstructioncited by 36
  33. 2022Geometry-aware Single-image Full-body Human Relightingcited by 34
  34. 2024MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videoscited by 34
  35. 2023Control4D: Efficient 4D Portrait Editing with Textcited by 32
  36. 2023SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Imagecited by 30
  37. 2024Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videoscited by 30
  38. 2024Generalizable Human Gaussians from Single-View Imagecited by 29

50 most cited of 246 All 246 (JSON)