mlsanityData to 7 Oct 2026

Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies

arXiv 1801.01615 ↗First posted 5 Jan 2018cs.CVcited by 239

Not on the map. Why?

Abstract (arXiv)

We present a unified deformation model for the markerless capture of multiple scales of human movement, including facial expressions, body motion, and hand gestures. An initial model is generated by locally stitching together models of the individual parts of the human body, which we refer to as the "Frankenstein" model. This model enables the full expression of part movements, including face and hands by a single seamless model. Using a large-scale capture of people wearing everyday clothes, we optimize the Frankenstein model to create "Adam". Adam is a calibrated model that shares the same skeleton hierarchy as the initial model but can express hair and clothing geometry, making it directly usable for fitting people as they normally appear in everyday life. Finally, we demonstrate the use of these models for total motion tracking, simultaneously capturing the large-scale body movements and the subtle face and hand motion of a social group of people.

Key facts. Cited by 239 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 60; 2022: 63; 2023: 62; 2024: 23; 2025: 20; 2026: 11.

239 papers.

Sort:

By area:

  1. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  2. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  3. 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
  4. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  5. 2022Generating Holistic 3D Human Motion from Speechcited by 180
  6. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  7. 2021FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integrationcited by 168
  8. 2022Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-timecited by 164
  9. 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 154
  10. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  11. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  12. 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
38 more
  1. 2022ARAH: Animatable Volume Rendering of Articulated Human SDFscited by 139
  2. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  3. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 136
  4. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
  5. 2022Structured Local Radiance Fields for Human Avatar Modelingcited by 116
  6. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 111
  7. 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
  8. 2023ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Renderingcited by 104
  9. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  10. 2021imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Posecited by 102
  11. 20233D Human Pose Estimation via Intuitive Physicscited by 100
  12. 2021Learning Motion Priors for 4D Human Body Capture in 3D Scenescited by 98
  13. 2022InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interactioncited by 90
  14. 2021NPMs: Neural Parametric Models for 3D Deformable Shapescited by 89
  15. 2024Expressive Whole-Body 3D Gaussian Avatarcited by 89
  16. 2021On Self-Contact and Human Posecited by 88
  17. 2023SHERF: Generalizable Human NeRF from a Single Imagecited by 88
  18. 2022Interacting Attention Graph for Single Image Two-Hand Reconstructioncited by 87
  19. 2023Hi4D: 4D Instance Segmentation of Close Human Interactioncited by 87
  20. 2022Capturing and Animation of Body and Clothing from Monocular Videocited by 83
  21. 2023AvatarReX: Real-time Expressive Full-body Avatarscited by 83
  22. 2021Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-Oncited by 81
  23. 2021Driving-Signal Aware Full-Body Avatarscited by 81
  24. 2022GIMO: Gaze-Informed Human Motion Prediction in Contextcited by 81
  25. 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
  26. 2023Neural Residual Radiance Fields for Streamably Free-Viewpoint Videoscited by 77
  27. 2023SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstructioncited by 77
  28. 2021SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elementscited by 72
  29. 2022gDNA: Towards Generative Detailed Neural Avatarscited by 72
  30. 2023HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splattingcited by 68
  31. 2021DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Camerascited by 67
  32. 2022UDE: A Unified Driving Engine for Human Motion Generationcited by 67
  33. 2025ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splattingcited by 67
  34. 2023X-Avatar: Expressive Human Avatarscited by 66
  35. 2022LISA: Learning Implicit Shape and Appearance of Handscited by 63
  36. 2021S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modelingcited by 59
  37. 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
  38. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 58

50 most cited of 239 All 239 (JSON)