mlsanityData to 7 Oct 2026

THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers

arXiv 2106.09336 ↗First posted 17 Jun 2021cs.CVcited by 50

Not on the map. Why?

Abstract (arXiv)

We present THUNDR, a transformer-based deep neural network methodology to reconstruct the 3d pose and shape of people, given monocular RGB images. Key to our methodology is an intermediate 3d marker representation, where we aim to combine the predictive power of model-free-output architectures and the regularizing, anthropometrically-preserving properties of a statistical human surface model like GHUM -- a recently introduced, expressive full body statistical 3d human model, trained end-to-end. Our novel transformer-based prediction pipeline can focus on image regions relevant to the task, supports self-supervised regimes, and ensures that solutions are consistent with human anthropometry. We show state-of-the-art results on Human3.6M and 3DPW, for both the fully-supervised and the self-supervised models, for the task of inferring 3d human shape, joint positions, and global translation. Moreover, we observe very solid 3d reconstruction performance for difficult human poses collected in the wild.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 17 Jun 2021.

Builds on

32 of 44 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  5. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  6. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  7. 2017End-to-end Recovery of Human Shape and Posecited by 883
  8. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  9. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  10. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  11. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  12. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
20 more
  1. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  2. 2017Integral Human Pose Regressioncited by 255
  3. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  4. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  5. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  6. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  7. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  8. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  9. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  10. 2020We are More than Our Joints: Predicting how 3D Bodies Movecited by 115
  11. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  12. 2019DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Comparecited by 100
  13. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  14. 2018Unsupervised Geometry-Aware Representation for 3D Human Pose Estimationcited by 73
  15. 2020Hierarchical Kinematic Human Mesh Recoverycited by 71
  16. 2020Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wildcited by 66
  17. 20203D Human Mesh Regression with Dense Correspondencecited by 66
  18. 2020Neural Descent for Visual 3D Human Pose and Shapecited by 60
  19. 20203D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Datacited by 50
  20. 2017Deep Multitask Architecture for Integrated 2D and 3D Human Sensingcited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 15; 2023: 20; 2024: 9; 2025: 2; 2026: 1.

50 papers.

Sort:

By area:

  1. 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
  2. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  3. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 152
  4. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  5. 2021GOAL: Generating 4D Whole-Body Motion for Hand-Object Graspingcited by 142
  6. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  7. 2023Human Motion Generation: A Surveycited by 95
  8. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 57
  9. 2022FLAG: Flow-based 3D Avatar Generation from Sparse Observationscited by 54
  10. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  11. 2022Differentiable Dynamics for Articulated 3d Human Motion Reconstructioncited by 38
  12. 2023Motion Flow Matching for Human Motion Synthesis and Editingcited by 36
38 more
  1. 2023PACE: Human and Camera Motion Estimation from in-the-wild Videoscited by 33
  2. 2023PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformerscited by 31
  3. 2023POTTER: Pooling Attention Transformer for Efficient Human Mesh Recoverycited by 31
  4. 2021HSPACE: Synthetic Parametric Humans Animated in Complex Environmentscited by 29
  5. 2022Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithmscited by 28
  6. 2022HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Drivingcited by 22
  7. 2024HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observationscited by 22
  8. 20223D Vision with Transformers: A Surveycited by 21
  9. 2023POCO: 3D Pose and Shape Estimation with Confidencecited by 20
  10. 2022Structured 3D Features for Reconstructing Controllable Avatarscited by 19
  11. 2023Scene-Aware 3D Multi-Human Motion Capture from a Single Cameracited by 19
  12. 2023HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observationscited by 17
  13. 2024COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimationcited by 15
  14. 2023Reconstructing Three-Dimensional Models of Interacting Humanscited by 14
  15. 2022BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimationcited by 13
  16. 2024DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humanscited by 13
  17. 2022MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstructioncited by 11
  18. 2022FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformERcited by 9
  19. 2022Self-supervised Human Mesh Recovery with Cross-Representation Alignmentcited by 9
  20. 2023LPFormer: LiDAR Pose Estimation Transformer with Multi-Task Networkcited by 9
  21. 2024STAF: 3D Human Mesh Recovery from Video with Spatio-Temporal Alignment Fusioncited by 9
  22. 2024SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimationcited by 9
  23. 2023Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstructioncited by 8
  24. 2023GATOR: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D Posecited by 4
  25. 2022Multi-view Human Body Mesh Translatorcited by 3
  26. 2022Human Body Measurement Estimation with Adversarial Augmentationcited by 3
  27. 2024Harmonious Group Choreography with Trajectory-Controllable Diffusioncited by 3
  28. 2023Utilizing Task-Generic Motion Prior to Recover Full-Body Motion from Very Sparse Signalscited by 2
  29. 2023ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attentioncited by 1
  30. 2023XFormer: Fast and Accurate Monocular 3D Body Capturecited by 1
  31. 2023Human Body Shape Classification Based on a Single Imagecited by 1
  32. 2023W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibrationcited by 1
  33. 2025Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forwardcited by 1
  34. 2023Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehiclecited by 0
  35. 2024Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Lossescited by 0
  36. 2024A Simple Strategy for Body Estimation from Partial-View Imagescited by 0
  37. 2025End-to-End Motion Capture from Rigid Body Markers with Geodesic Losscited by 0
  38. 2026Listen to Rhythm, Choose Movements: Autoregressive Multimodal Dance Generation via Diffusion and Mamba with Decoupled Dance Datasetcited by 0