mlsanityData to 7 Oct 2026

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

arXiv 1904.05866 ↗First posted 11 Apr 2019cs.CVcited by 1,600

Not on the map. Why?

Cited by 168 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

To facilitate the analysis of human actions, interactions and emotions, we compute a 3D model of human body pose, hand pose, and facial expression from a single monocular image. To achieve this, we use thousands of 3D scans to train a new, unified, 3D model of the human body, SMPL-X, that extends SMPL with fully articulated hands and an expressive face. Learning to regress the parameters of SMPL-X directly from images is challenging without paired images and 3D ground truth. Consequently, we follow the approach of SMPLify, which estimates 2D features and then optimizes model parameters to fit the features. We improve on SMPLify in several significant ways: (1) we detect 2D features corresponding to the face, hands, and feet and fit the full SMPL-X model to these; (2) we train a new neural network pose prior using a large MoCap dataset; (3) we define a new interpenetration penalty that is both fast and accurate; (4) we automatically detect gender and the appropriate body models (male, female, or neutral); (5) our PyTorch implementation achieves a speedup of more than 8x over Chumpy. We use the new method, SMPLify-X, to fit SMPL-X to both controlled images and images in the wild. We evaluate 3D accuracy on a new curated dataset comprising 100 images with pseudo ground-truth. This is a step towards automatic expressive human capture from monocular RGB data. The models, code, and data are available for research purposes at https://smpl-x.is.tue.mpg.de.

Key facts. Cited by 1,600 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 121; 2022: 167; 2023: 295; 2024: 341; 2025: 354; 2026: 322.

1,600 papers.

Sort:

By area:

  1. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  2. 2022Human Motion Diffusion Modelcited by 1,062
  3. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  4. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  5. 2023MotionGPT: Human Motion as a Foreign Languagecited by 521
  6. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  7. 2022MotionCLIP: Exposing Human Motion Generation to CLIP Spacecited by 406
  8. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
  9. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  10. 2023Human Motion Diffusion as a Generative Priorcited by 354
  11. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  12. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
38 more
  1. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  2. 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 306
  3. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  4. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 274
  5. 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
  6. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  7. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  8. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  9. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 221
  10. 2023Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Datasetcited by 220
  11. 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 220
  12. 2023Object Motion Guided Human Motion Synthesiscited by 206
  13. 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 205
  14. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 203
  15. 2021Stochastic Scene-Aware Motion Predictioncited by 203
  16. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 200
  17. 2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
  18. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  19. 2023GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussianscited by 190
  20. 2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
  21. 2022Generating Holistic 3D Human Motion from Speechcited by 180
  22. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  23. 2024SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splattingcited by 171
  24. 2021FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integrationcited by 168
  25. 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 164
  26. 2022HUMANISE: Language-conditioned Human Motion Generation in 3D Scenescited by 156
  27. 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 154
  28. 2023DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Modelscited by 154
  29. 2023SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimationcited by 154
  30. 2023HUGS: Human Gaussian Splatscited by 154
  31. 2021Probabilistic Modeling for Human Mesh Recoverycited by 152
  32. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  33. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  34. 2021GOAL: Generating 4D Whole-Body Motion for Hand-Object Graspingcited by 142
  35. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 141
  36. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 140
  37. 2022ARAH: Animatable Volume Rendering of Articulated Human SDFscited by 139
  38. 2022InstantAvatar: Learning Avatars from Monocular Video in 60 Secondscited by 138

50 most cited of 1,600 All 1,600 (JSON)