Research map / 3D vision / Human pose estimation
AMASS: Archive of Motion Capture As Surface Shapes
Naureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll, 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 |
|---|---|---|---|
| replace MoSh with MoSh++ (SMPL body model, tuned hyperparameters) | MoSh · SSM shape estimation (46 markers) | scan-to-mesh distance (mm): 12.1mm -> 7.4mm | Improved |
| replace MoSh with MoSh++ for pose estimation | MoSh · SSM pose estimation (46 markers) | scan-to-mesh distance (mm): 10.5mm -> 8.1mm | Improved |
| add DMPL soft-tissue dynamics terms (ablation) | MoSh++ · SSM pose estimation (46 markers) | scan-to-mesh distance (mm): 8.1mm -> 7.3mm | Improved |
| replace MoSh with MoSh++ with dynamics | MoSh · SSM pose estimation with dynamics (46 markers) | scan-to-mesh distance (mm): 10.24mm -> 7.3mm | Improved |
| increase number of shape and dynamics coefficients beyond 16 and 8 (ablation) | MoSh++ · SSM shape estimation | scan-to-mesh distance to ground truth | Hurt |
| add missing-marker-dependent pose prior weight q (ablation) | MoSh++ · Pose estimation under heavy marker occlusion | pose plausibility (qualitative) | Improved |
| add hand articulation with SMPL-H and MANO (ablation) | MoSh++ · TCD Hand dataset | hand pose realism (qualitative) | Improved |
| use 46-marker set instead of 67 for MoSh++ (ablation) | MoSh++ · SSM | scan-to-mesh distance | No clear effect |
Closest papers by meaning
- Monocular Total Capture: Posing Face, Body, and Hands in the Wild (CVPR 2019 · similarity 0.88)
- MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos (CVPR 2026 · similarity 0.88)
- SOMA: Solving Optical Marker-Based MoCap Automatically (ICCV 2021 · similarity 0.88)
- MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond (CVPR 2025 · similarity 0.87)
- MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling (NeurIPS 2024 · similarity 0.86)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 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.
