mlsanityData to 14 Oct 2026

Reconstructing Humans with a Biomechanically Accurate Skeleton

arXiv 2503.21751 ↗First posted 27 Mar 2025cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce a method for reconstructing 3D humans from a single image using a biomechanically accurate skeleton model. To achieve this, we train a transformer that takes an image as input and estimates the parameters of the model. Due to the lack of training data for this task, we build a pipeline to produce pseudo ground truth model parameters for single images and implement a training procedure that iteratively refines these pseudo labels. Compared to state-of-the-art methods for 3D human mesh recovery, our model achieves competitive performance on standard benchmarks, while it significantly outperforms them in settings with extreme 3D poses and viewpoints. Additionally, we show that previous reconstruction methods frequently violate joint angle limits, leading to unnatural rotations. In contrast, our approach leverages the biomechanically plausible degrees of freedom making more realistic joint rotation estimates. We validate our approach across multiple human pose estimation benchmarks. We make the code, models and data available at: https://isshikihugh.github.io/HSMR/

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 47 of its 69 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

47 of 69 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  7. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  8. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  9. 2017End-to-end Recovery of Human Shape and Posecited by 885
  10. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  11. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  12. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
35 more
  1. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  2. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
  3. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
  4. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  5. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 350
  6. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  7. 2018Learning 3D Human Dynamics from Videocited by 316
  8. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  9. 2023Reconstructing Hands in 3D with Transformerscited by 306
  10. 2024Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidancecited by 272
  11. 2017Integral Human Pose Regressioncited by 256
  12. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  13. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 236
  14. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  15. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  16. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  17. 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 185
  18. 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 181
  19. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  20. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  21. 2023SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimationcited by 155
  22. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 135
  23. 20233D Human Pose Estimation via Intuitive Physicscited by 103
  24. 2019xR-EgoPose: Egocentric 3D Human Pose from an HMD Cameracited by 79
  25. 2017AI Challenger : A Large-scale Dataset for Going Deeper in Image Understandingcited by 73
  26. 2024Humanoid Locomotion as Next Token Predictioncited by 69
  27. 2024OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitationcited by 67
  28. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 59
  29. 2017MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Priorcited by 36
  30. 2022SUPR: A Sparse Unified Part-Based Human Representationcited by 21
  31. 2022PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimationcited by 18
  32. 2024MultiPhys: Multi-Person Physics-aware 3D Motion Estimationcited by 18
  33. 2023Towards Single Camera Human 3D-Kinematicscited by 8
  34. 2024OpenCapBench: A Benchmark to Bridge Pose Estimation and Biomechanicscited by 7
  35. 20243D Kinematics Estimation from Video with a Biomechanical Model and Synthetic Training Datacited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 16.

22 papers.

Sort:

  1. 2025Portable Biomechanics Laboratory: Clinically Accessible Movement Analysis from a Handheld Smartphonecited by 8
  2. 2026Monocular Biomechanical Tracking of Fingers with Inverse Kinematics to Foundation Modelscited by 5
  3. 2026PEAR: Pixel-aligned Expressive humAn mesh Recoverycited by 3
  4. 20254D-MoDe: Towards Editable and Scalable Volumetric Streaming via Motion-Decoupled 4D Gaussian Compressioncited by 2
  5. 2025SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recoverycited by 2
  6. 2026OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robotscited by 2
  7. 2025MonoMSK: Monocular 3D Musculoskeletal Dynamics Estimationcited by 1
  8. 2025Investigating Anthropometric Fidelity in SAM 3D Bodycited by 1
  9. 2026SAM4Dcap: Training-free Biomechanical Twin System from Monocular Videocited by 1
  10. 2026BioGait-VLM: A Tri-Modal Vision-Language-Biomechanics Framework for Interpretable Clinical Gait Assessmentcited by 1
  11. 2026GraphiContact: Pose-aware Human-Scene Robust Contact Perception for Interactive Systemscited by 1
  12. 2026MoViD: View-Invariant 3D Human Pose Estimation via Motion-View Disentanglementcited by 1
10 more
  1. 2026Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Modelcited by 1
  2. 2025Graphics4Science: Computer Graphics for Scientific Impactscited by 0
  3. 2026Constrained Dynamic Gaussian Splattingcited by 0
  4. 2026Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videoscited by 0
  5. 2026BioHuman: Learning Biomechanical Human Representations from Videocited by 0
  6. 2026SOMA: From Surface Observations to Muscle Anatomycited by 0
  7. 2026Again-Pose: Anchor-Guided Adaptive Inter-Frame Motion Cues Propagating for High-quality Human Pose Reconstructioncited by 0
  8. 2026Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Predictioncited by 0
  9. 2026Revisiting Euler-Angle Regression with Kolmogorov-Arnold Networkscited by 0
  10. 2026Direct Clinical Joint Angle Extraction from Parametric Body Model Rotation Matricescited by 0