Research map / 3D vision / Human pose estimation
BodyPressure - Inferring Body Pose and Contact Pressure From a Depth Image
Henry Clever, Patrick L. Grady, Greg Turk, Charles C. Kemp
Read the paperCheck 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 |
|---|---|---|---|
| use depth-only BPWnet instead of multimodal Pyramid Fusion | BPWnet · SLP test (22 subjects) pose | MPJPE (mm): 79.64 -> 69.36 | Improved |
| train on mixed synthetic and real data instead of real only | BPWnet · SLP test (22 subjects) pose | MPJPE (mm): 104.20 -> 69.36 | Improved |
| train on mixed data instead of synthetic only | BPWnet · SLP test (22 subjects) pose | MPJPE (mm): 105.90 -> 69.36 | Improved |
| add mixed real and synthetic training data | BPWnet · SLP test (22 subjects) pressure image | MSE (kPa^2): 1.456 -> 1.184 | Improved |
| add SMPL model joint learning to BPBnet (ablation) | BPBnet · SLP test (22 subjects) pressure image | MSE (kPa^2): 0.905 -> 0.838 | Improved |
| use white-box BPWnet instead of black-box BPBnet for pose | BPWnet · SLP test (22 subjects) pose | MPJPE (mm): 74.54 -> 69.36 | Improved |
| use white-box BPWnet instead of black-box BPBnet for pressure image | BPWnet · SLP test (22 subjects) pressure image | MSE (kPa^2): 0.838 -> 1.184 | Hurt |
| use white-box BPWnet instead of BPBnet for pressure on the body mesh | BPWnet · SLP test (22 subjects) v2vP | MSE (kPa^2): 2.872 -> 2.849 | Improved |
| add DMR residual learning (ablation) | BPWnet · SLP test (22 subjects) pose | MPJPE (mm): 72.84 -> 69.36 | Improved |
| add DMR residual learning (ablation) | BPWnet · SLP test (22 subjects) body mass | MAE (kg): 7.42 -> 5.64 | Improved |
| add BetaNet (ablation) | BPWnet · SLP test (22 subjects) pose | MPJPE (mm): 68.62 -> 69.36 | Hurt |
| add BetaNet (ablation) | BPWnet · SLP test (22 subjects) body height | MAE (mm): 65.97 -> 39.45 | Improved |
Closest papers by meaning
- Bodies at Rest: 3D Human Pose and Shape Estimation From a Pressure Image Using Synthetic Data (CVPR 2020 · similarity 0.91)
- BodyMAP - Jointly Predicting Body Mesh and 3D Applied Pressure Map for People in Bed (CVPR 2024 · similarity 0.91)
- PI-HMR: Towards Robust In-bed Temporal Human Shape Reconstruction with Contact Pressure Sensing (CVPR 2025 · similarity 0.87)
- DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery (CVPR 2025 · similarity 0.85)
- MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond (CVPR 2025 · similarity 0.83)
- EgoPressure: A Dataset for Hand Pressure and Pose Estimation in Egocentric Vision (CVPR 2025 · similarity 0.82)
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.
