Research map / 3D vision / Human pose estimation
Bodies at Rest: 3D Human Pose and Shape Estimation From a Pressure Image Using Synthetic Data
Henry M. Clever, Zackory Erickson, Ariel Kapusta, Greg Turk, Karen Liu, Charles C. Kemp
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add the pressure map reconstruction network (ablation) | PressureNet · Synthetic and real test sets | 3DVPE (cm): 4.38 -> 3.94 (synthetic); 5.33 -> 4.99 (1K real); 4.94 -> 4.76 (99 real) | Improved |
| Add training-data noise (ablation) | PressureNet · Synthetic and real test sets | 3DVPE (cm): 3.97 -> 3.94 (synthetic); 5.05 -> 4.99 (1K real); 4.79 -> 4.76 (99 real) | Improved |
| Add edge and contact input channels (ablation) | PressureNet · Synthetic and real test sets | 3DVPE (cm): 4.03 -> 3.94 (synthetic); 5.07 -> 4.99 (1K real); 4.85 -> 4.76 (99 real) | Improved |
| Increase training data from 46K to 184K images (ablation) | PressureNet · Synthetic and real test sets | 3DVPE (cm): 4.35 -> 3.94 (synthetic); 5.17 -> 4.99 (1K real); 4.89 -> 4.76 (99 real) | Improved |
Closest papers by meaning
- BodyPressure - Inferring Body Pose and Contact Pressure From a Depth Image (TPAMI 2022 · similarity 0.91)
- BodyMAP - Jointly Predicting Body Mesh and 3D Applied Pressure Map for People in Bed (CVPR 2024 · similarity 0.90)
- PI-HMR: Towards Robust In-bed Temporal Human Shape Reconstruction with Contact Pressure Sensing (CVPR 2025 · similarity 0.89)
- BodyNet: Volumetric Inference of 3D Human Body Shapes (ECCV 2018 · similarity 0.87)
- DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery (CVPR 2025 · similarity 0.87)
- From Image to Stability: Learning Dynamics from Human Pose (ECCV 2020 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
