Research map / 3D vision / Human pose estimation
On Self-Contact and Human Pose
Lea Muller, Ahmed A. A. Osman, Siyu Tang, Chun-Hao P. Huang, Michael J. Black
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 |
|---|---|---|---|
| Train SPIN with MTP and DSC data and use contact-aware fitting | SPIN · 3DPW | MPJPE: 96.9 -> 84.9 | Improved |
| Train SPIN with MTP and DSC data and use contact-aware fitting | SPIN · 3DPW | PA-MPJPE: 59.2 -> 55.5 | Improved |
| Train SPIN with MTP and DSC data and use contact-aware fitting | SPIN · MPI-INF-3DHP (MI) | PA-MPJPE: 67.5 -> 68.6 | Hurt |
| Train SPIN with MTP and DSC data and use contact-aware fitting | SPIN · 3DCP Scan | MPJPE: 79.7 -> 69.5 | Improved |
| Train SPIN with MTP and DSC data and use contact-aware fitting | SPIN · 3DCP Scan | PA-MPJPE: 50.6 -> 42.5 | Improved |
| Add MTP pose-mimicking training data (ablation) | SPIN · 3DPW | MPJPE: 96.9 -> 88.7 | Improved |
| Add DSC training data to MTP training (ablation) | TUCH (MTP) · 3DPW | MPJPE: 88.7 -> 84.9 | Improved |
| Add DSC training data to MTP training (ablation) | TUCH (MTP) · 3DPW | PA-MPJPE: 57.4 -> 55.5 | Improved |
| Use SMPLify-XMC pseudo-ground-truth for MTP instead of standard fitting (ablation) | S+ · 3DPW | MPJPE: 96.1 -> 85.0 | Improved |
| Use contact-aware fitting and contact supervision rather than standard SMPLify (ablation) | S+ · 3DPW | MPJPE: 96.1 -> 84.9 | Improved |
| Use MTP and DSC annotations with exemplar fine-tuning and contact loss | HMR-EFT · 3DPW | MPJPE: 85.3 -> 82.3 | Improved |
| Use MTP and DSC annotations with exemplar fine-tuning and contact loss | HMR-EFT · 3DCP Scan | MPJPE: 71.4 -> 73.4 | Hurt |
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.
- SPIN — SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition (AAAI 2021) · better on 5 of 6 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
- Learning Complex 3D Human Self-Contact (AAAI 2021 · similarity 0.92)
- Generative Modeling of Shape-Dependent Self-Contact Human Poses (ICCV 2025 · similarity 0.92)
- Pose Priors from Language Models (CVPR 2025 · similarity 0.89)
- PICO: Reconstructing 3D People In Contact with Objects (CVPR 2025 · similarity 0.87)
- SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation (CVPR 2024 · similarity 0.87)
- ContactField: Implicit Field Representation for Multi-Person Interaction Geometry (NeurIPS 2024 · similarity 0.86)
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.
