Research map / 3D vision / Human pose estimation
General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues
Helge Rhodin, Nadia Robertini, Dan Casas, Christian Richardt, Hans-Peter Seidel, 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 Stage II shape refinement after Stage I (ablation) | Stage I estimate · shape overlap on HumanEva-I | shape accuracy | Improved |
| train the pose model on HumanEva sequences instead of general data | Our method · HumanEva-I S1 Walk | mean joint error (mm): 74.9 -> 54.6 | Improved |
| train the pose model on HumanEva sequences instead of general data | Our method · HumanEva-I S2 Box | mean joint error (mm): 59.7 -> 35.1 | Improved |
| compensate joint offset between ground truth and estimate using first frame | Our method · HumanEva-I | mean joint error: 6-7 cm -> 3-5 cm | Improved |
| use general training instead of Amin-style subject-specific training | Our method vs Amin 2013 · HumanEva-I S2 Box | mean joint error (mm): 47.7 -> 35.1 | Improved |
Closest papers by meaning
- Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation From Monocular Video (CVPR 2022 · similarity 0.89)
- Real-Time Simultaneous Pose and Shape Estimation for Articulated Objects Using a Single Depth Camera (TPAMI 2016 · similarity 0.89)
- Monocular Total Capture: Posing Face, Body, and Hands in the Wild (CVPR 2019 · similarity 0.89)
- Video Based Reconstruction of 3D People Models (CVPR 2018 · similarity 0.88)
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 2025 · similarity 0.87)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.87)
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.
