Research map / 3D vision / Human pose estimation
Global-to-Local Modeling for Video-Based 3D Human Pose and Shape Estimation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 single coupled temporal modeling with global-to-local modeling | GLoT · 3DPW | PA-MPJPE: 52.1 -> 50.6 | Helped |
| Replace single coupled temporal modeling with global-to-local modeling | GLoT · MPI-INF-3DHP | MPJPE: 96.7 -> 93.9 | Helped |
| Replace single coupled temporal modeling with global-to-local modeling | GLoT · Human3.6M | PA-MPJPE: 47.4 -> 46.3 | Helped |
| Add Local Parameter Correction to Global Motion Modeling (ablation) | GLoT · 3DPW | PA-MPJPE: 52.6 -> 50.6 | Helped |
| Use masked pose and shape estimation rather than no masking (ablation) | GLoT · 3DPW | MPJPE: 82.3 -> 80.7 | Helped |
| Increase masking to 87.5% rather than 0% (ablation) | GLoT · 3DPW | Accel: 7.3 -> 6.5 | Helped |
| Increase masking to 87.5% rather than 0% (ablation) | GLoT · 3DPW | PA-MPJPE: 51.7 -> 52.8 | Hurt |
| Use an SMPL mean-template mask token instead of a learnable token (ablation) | GLoT · 3DPW | PA-MPJPE: 51.5 -> 50.6 | Helped |
| Use HSCR instead of a residual connection (ablation) | GLoT · 3DPW | MPJPE: 81.7 -> 80.7 | Helped |
| Set nearby-frame length to 4 rather than 2 (ablation) | GLoT · 3DPW | PA-MPJPE: 51.9 -> 50.6 | Helped |
| Set nearby-frame length to 4 rather than 2 (ablation) | GLoT · 3DPW | MPJPE: 83 -> 80.7 | Mixed |
| Detach the global-estimation gradient path into HSCR (ablation) | GLoT · 3DPW | PA-MPJPE: 50.9 -> 50.6 | Helped |
Closest papers by meaning
- PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space Model (AAAI 2025 · similarity 0.89)
- SVTformer: Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation (AAAI 2025 · similarity 0.89)
- Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation (NeurIPS 2024 · similarity 0.88)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 2025 · similarity 0.88)
- HiPoser: 3D Human Pose Estimation with Hierarchical Shared Learning at Parts-Level Using Inertial Measurement Units (AAAI 2025 · similarity 0.88)
- Can Generative Video Models Help Pose Estimation? (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.