Research map / 3D vision / Human pose estimation
HULC: 3D HUman Motion Capture with Pose Manifold SampLing and Dense Contact Guidance
Soshi Shimada, Vladislav Golyanik, Zhi Li, Patrick Pérez, Weipeng Xu, Christian Theobalt
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 pose manifold sampling optimisation (ablation) | HULC · GPA (no Procrustes) | MPJPE (mm): 221.3 -> 217.9 | Improved |
| add final refinement (ablation) | HULC · GPA (no Procrustes) | MPJPE (mm): 240.8 -> 217.9 | Improved |
| add sampling optimisation without refinement over neither (ablation) | HULC · GPA (no Procrustes) | MPJPE (mm): 251.1 -> 240.8 | Improved |
| add sampling optimisation (ablation) | HULC · GPA | non-penetration (%): 97.6 -> 99.4 | Improved |
| add sampling optimisation (ablation) | HULC · PROX | non-penetration (%): 93.8 -> 97.0 | Improved |
| add contact loss term to the optimisation (+10m init) (ablation) | HULC contact-based optimisation · GPA global translation | error (m): 2.861 -> 0.244 | Improved |
| add contact loss term (+10m init) (ablation) | HULC contact-based optimisation · GPA absolute bone length | error (m): 1.918 -> 0.109 | Improved |
| add refinement (ablation) | HULC · GPA | e_smooth: 24.7 -> 20.2 | Improved |
| add sliding loss (ablation) | HULC · GPA | sliding error (mm): 18.5 -> 16.0 | Improved |
| add sliding loss (ablation) | HULC · GPA | MPJPE (mm): 220.2 -> 217.9 | Improved |
| add confidence-based pose merging (ablation) | HULC sampling · GPA | MPJPE (mm): 249.1 -> 245.5 | Improved |
| replace random sampling with learned manifold sampling (ablation) | HULC sampling · GPA | MPJPE (mm): ~15x fewer samples | Improved |
Closest papers by meaning
- MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior (TPAMI 2018 · similarity 0.86)
- MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond (CVPR 2025 · similarity 0.86)
- Mocap-2-to-3: Multi-view Lifting for Monocular Motion Recovery with 2D Pretraining (CVPR 2026 · similarity 0.86)
- SOMA: Solving Optical Marker-Based MoCap Automatically (ICCV 2021 · similarity 0.85)
- InteractVLM: 3D Interaction Reasoning from 2D Foundational Models (CVPR 2025 · similarity 0.84)
- EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams (CVPR 2024 · 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.
