Research map / 3D vision / Human pose estimation
Contact-Aware Refinement of Human Pose Pseudo-Ground Truth via Bioimpedance Sensing
Maria-Paola Forte, Nikos Athanasiou, Giulia Ballardini, Jan Ulrich Bartels, Katherine J. Kuchenbecker, Michael J. Black
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 |
|---|---|---|---|
| add BioTUCH (2D + contact loss) refinement | Multi-HMR · Self-contact dataset (arm region) | PA-V2V (mm): 57.46 -> 50.21 | Improved |
| add BioTUCH refinement | AiOS · Self-contact dataset (arm region) | PA-V2V (mm): 72.24 -> 62.79 | Improved |
| add BioTUCH refinement | TUCH · Self-contact dataset (arm region) | PA-V2V (mm): 70.55 -> 63.99 | Improved |
| add BioTUCH refinement | three input methods · Self-contact dataset (arm region) | PA-V2V: average 11.7% improvement | Improved |
| add BioTUCH refinement | three input methods · Self-contact dataset (arm region) | contact detection rate: average improvement of 31.60 percentage points | Improved |
| add BioTUCH refinement | three input methods · Self-contact dataset (arm region) | V-Distance (mm): average reduction of 15.39 mm | Improved |
| add BioTUCH refinement | three input methods · Self-contact dataset (arm region) | shoulder and elbow joint error: 0.36 mm and 0.50 mm degradation | Hurt |
| add BioTUCH refinement | three input methods · Self-contact dataset (arm region) | wrist joint error: 8.85 mm improvement | Improved |
| add contact loss on top of 2D loss (ablation) | Multi-HMR + BioTUCH · Self-contact dataset (arm region) | PA-V2V (mm): 77.41 -> 50.21 | Improved |
| add 2D loss alone to the baseline (ablation) | Multi-HMR · Self-contact dataset (arm region) | PA-V2V (mm): 57.46 -> 77.41 | Hurt |
| add 2D loss alone to the baseline (ablation) | AiOS · Self-contact dataset (arm region) | PA-V2V (mm): 72.24 -> 86.61 | Hurt |
| add 2D loss to the contact loss (ablation) | Multi-HMR · Self-contact dataset (arm region) | contact detection rate (%): 79.35 -> 78.34 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- AiOS — AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation (CVPR 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- On Self-Contact and Human Pose (CVPR 2021 · similarity 0.88)
- DECO: Dense Estimation of 3D Human-Scene Contact In The Wild (ICCV 2023 · similarity 0.86)
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.84)
- Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation (CVPR 2025 · similarity 0.84)
- Hand-held Object Reconstruction from RGB Video with Dynamic Interaction (CVPR 2025 · similarity 0.84)
- Pose Priors from Language Models (CVPR 2025 · similarity 0.84)
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.
