mlsanityData to 14 Oct 2026

BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Image

arXiv 2105.09936 ↗First posted 20 May 2021cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Contact pressure between the human body and its surroundings has important implications. For example, it plays a role in comfort, safety, posture, and health. We present a method that infers contact pressure between a human body and a mattress from a depth image. Specifically, we focus on using a depth image from a downward facing camera to infer pressure on a body at rest in bed occluded by bedding, which is directly applicable to the prevention of pressure injuries in healthcare. Our approach involves augmenting a real dataset with synthetic data generated via a soft-body physics simulation of a human body, a mattress, a pressure sensing mat, and a blanket. We introduce a novel deep network that we trained on an augmented dataset and evaluated with real data. The network contains an embedded human body mesh model and uses a white-box model of depth and pressure image generation. Our network successfully infers body pose, outperforming prior work. It also infers contact pressure across a 3D mesh model of the human body, which is a novel capability, and does so in the presence of occlusion from blankets.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 49 of its 87 references that are in the map. First posted on arXiv 20 May 2021.

Builds on

49 of 87 references.

References · 49

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2017Random Erasing Data Augmentationcited by 1,239
  4. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  5. 2017End-to-end Recovery of Human Shape and Posecited by 885
  6. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  8. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  9. 2019Learning joint reconstruction of hands and manipulated objectscited by 378
  10. 2017Learning from Synthetic Humanscited by 359
  11. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 319
  12. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 307
37 more
  1. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
  2. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 295
  3. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  4. 2020Deep Learning-Based Human Pose Estimation: A Surveycited by 207
  5. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  6. 2021ContactOpt: Optimizing Contact to Improve Graspscited by 139
  7. 2018Sim-to-Real Reinforcement Learning for Deformable Object Manipulationcited by 131
  8. 2019Generating 3D People in Scenes without Peoplecited by 127
  9. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  10. 2021LEAP: Learning Articulated Occupancy of Peoplecited by 107
  11. 2019Structured Prediction Helps 3D Human Motion Modellingcited by 96
  12. 2021On Self-Contact and Human Posecited by 89
  13. 2018Unsupervised Geometry-Aware Representation for 3D Human Pose Estimationcited by 73
  14. 2016Synthesizing Training Images for Boosting Human 3D Pose Estimationcited by 52
  15. 2016Human pose estimation via Convolutional Part Heatmap Regressioncited by 51
  16. 2019Assistive Gym: A Physics Simulation Framework for Assistive Roboticscited by 44
  17. 2019SimulCap : Single-View Human Performance Capture with Cloth Simulationcited by 41
  18. 2016Deep Kinematic Pose Regressioncited by 40
  19. 2019Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Controlcited by 40
  20. 2020Learning Complex 3D Human Self-Contactcited by 40
  21. 2017MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Priorcited by 36
  22. 2020Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Datacited by 34
  23. 2019Learning Multi-Human Optical Flowcited by 26
  24. 2018Learning Depth from Single Images with Deep Neural Network Embedding Focal Lengthcited by 25
  25. 2016Training a Feedback Loop for Hand Pose Estimationcited by 21
  26. 2019Seeing Under the Cover: A Physics Guided Learning Approach for In-Bed Pose Estimationcited by 17
  27. 2017DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognitioncited by 15
  28. 2020Multimodal In-bed Pose and Shape Estimation under the Blanketscited by 15
  29. 20183D Human Pose Estimation on a Configurable Bed from a Pressure Imagecited by 13
  30. 2017Deep Haptic Model Predictive Control for Robot-Assisted Dressingcited by 12
  31. 2017In-Bed Pose Estimation: Deep Learning with Shallow Datasetcited by 11
  32. 2018Keep it Unreal: Bridging the Realism Gap for 2.5D Recognition with Geometry Priors Onlycited by 9
  33. 2020Cloth in the Wind: A Case Study of Physical Measurement through Simulationcited by 9
  34. 2020Simultaneously-Collected Multimodal Lying Pose Dataset: Towards In-Bed Human Pose Monitoring under Adverse Vision Conditionscited by 9
  35. 2016Understanding and Exploiting Object Interaction Landscapescited by 8
  36. 2017Learning to Navigate Cloth using Hapticscited by 4
  37. 2019Real-time Convolutional Networks for Depth-based Human Pose Estimationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 2; 2024: 3; 2025: 7; 2026: 2.

20 papers.

Sort:

By area:

  1. 2022Object Detection Using Sim2Real Domain Randomization for Robotic Applicationscited by 25
  2. 2022PressureVision: Estimating Hand Pressure from a Single RGB Imagecited by 23
  3. 2022Self-supervised Human Mesh Recovery with Cross-Representation Alignmentcited by 9
  4. 2022Anatomy-guided domain adaptation for 3D in-bed human pose estimationcited by 9
  5. 2023PresSim: An End-to-end Framework for Dynamic Ground Pressure Profile Generation from Monocular Videos Using Physics-based 3D Simulationcited by 9
  6. 2024DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Imagecited by 9
  7. 2022Under the Cover Infant Pose Estimation using Multimodal Datacited by 6
  8. 2025DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recoverycited by 6
  9. 2024BodyMAP -- Jointly Predicting Body Mesh and 3D Applied Pressure Map for People in Bedcited by 5
  10. 2024Text me the data: Generating Ground Pressure Sequence from Textual Descriptions for HARcited by 3
  11. 2022BlanketGen - A synthetic blanket occlusion augmentation pipeline for MoCap datasetscited by 1
  12. 2023PressureTransferNet: Human Attribute Guided Dynamic Ground Pressure Profile Transfer using 3D simulated Pressure Mapscited by 1
8 more
  1. 2025TxP: Reciprocal Generation of Ground Pressure Dynamics and Activity Descriptions for Improving Human Activity Recognitioncited by 1
  2. 2026PressMimic: Pressure-Guided Motion Capture and Control for Humanoid Robot Imitationcited by 1
  3. 2025BlanketGen2-Fit3D: Synthetic Blanket Augmentation Towards Improving Real-World In-Bed Blanket Occluded Human Pose Estimationcited by 0
  4. 2025Multi-modal 3D Pose and Shape Estimation with Computed Tomographycited by 0
  5. 2025ChairPose: Pressure-based Chair Morphology Grounded Sitting Pose Estimation through Simulation-Assisted Trainingcited by 0
  6. 2025Pressure2Motion: Hierarchical Human Motion Reconstruction from Ground Pressure with Text Guidancecited by 0
  7. 2025Improving the Plausibility of Pressure Distributions Synthesized from Depth Image through Generative Modelingcited by 0
  8. 2026Patient4D: Temporally Consistent Patient Body Mesh Recovery from Monocular Operating Room Videocited by 0