Research map / 3D vision / Human pose estimation
Learning Complex 3D Human Self-Contact
Mihai Fieraru, Mihai Zanfir, Elisabeta Oneata, Alin-Ionut Popa, Vlad Olaru, Cristian Sminchisescu
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 SCP rather than adapted ISP for self-contact signature prediction | self-contact estimation · FlickrSC3D (IoU_75) | signature IoU: 0.133 -> 0.301 | Improved |
| Add geometric self-contact consistency loss L_G (ablation) | 3D human reconstruction · HumanSC3D overall | MPJPE (P, mm): 114.4 -> 98.2 | Improved |
| Add geometric self-contact consistency loss L_G (ablation) | 3D human reconstruction · HumanSC3D overall | contact distance error (C, mm): 203.4 -> 16.4 | Improved |
| Train SCP specifically for hand-to-face contact rather than general self-contact | SCP hand-to-face detection · HumanSC3D hand-to-face detection | recall: 46% -> 53% | Improved |
| Remove separation loss L_sep (ablation) | SCP · FlickrSC3D (IoU_75) | signature IoU: 0.301 -> 0.289 | Hurt |
| Remove image-support supervision L_K along with L_sep (ablation) | SCP · FlickrSC3D (IoU_75) | signature IoU: 0.301 -> 0.236 | Hurt |
| Remove image-support consistency filtering at inference (ablation) | SCP signature prediction · FlickrSC3D (IoU_75) | signature IoU: 0.301 -> 0.244 | Hurt |
| Remove image-support supervision L_K as well as L_sep (ablation) | SCP image-support prediction · FlickrSC3D | error (pixels): 13.6 -> 70.6 | Hurt |
| Remove image-support supervision L_K as well as L_sep (ablation) | SCP image-support prediction · HumanSC3D | error (pixels): 10.3 -> 61.0 | Hurt |
| Remove separation loss L_sep (ablation) | SCP image-support prediction · FlickrSC3D | error (pixels): 13.6 -> 12.8 | No clear effect |
| Remove separation loss L_sep (ablation) | SCP image-support prediction · HumanSC3D | error (pixels): 10.3 -> 9.2 | No clear effect |
Closest papers by meaning
- ContactField: Implicit Field Representation for Multi-Person Interaction Geometry (NeurIPS 2024 · similarity 0.88)
- Pose Priors from Language Models (CVPR 2025 · similarity 0.88)
- Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images (AAAI 2024 · similarity 0.88)
- InteractVLM: 3D Interaction Reasoning from 2D Foundational Models (CVPR 2025 · similarity 0.87)
- PICO: Reconstructing 3D People In Contact with Objects (CVPR 2025 · similarity 0.87)
- Learning Dense Hand Contact Estimation from Imbalanced Data (NeurIPS 2025 · 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.
