Research map / 3D vision / Human pose estimation
AGORA: Avatars in Geography Optimized for Regression Analysis
Check 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 |
|---|---|---|---|
| Fine-tune pretrained SPIN on AGORA rather than use SPIN-pt | SPIN · 3DPW testset (14 joints) | MPJPE: 96.9 -> 85.7 | Helped |
| Fine-tune pretrained SPIN on AGORA rather than use SPIN-pt | SPIN · 3DPW testset (14 joints) | PA-MPJPE: 59.3 -> 55.3 | Helped |
| Fine-tune pretrained SPIN on AGORA rather than use SPIN-pt | SPIN · AGORA testset (24 joints) | MPJPE: 175.1 -> 153.4 | Helped |
| Fine-tune SPIN on AGORA instead of EFT data | SPIN · 3DPW testset (14 joints) | MPJPE: 97.4 -> 85.7 | Helped |
| Fine-tune SPIN on AGORA instead of EFT data | SPIN · AGORA testset (24 joints) | MPJPE: 173.7 -> 153.4 | Helped |
| Use AGORA training images for fine-tuning | SPIN · High-occlusion cases in AGORA | MPJPE | Helped |
| Interpolate the adult SMPL-X template with the infant SMIL template for child fits (ablation) | SMPL-X child fitting · Child scan fitting | body shape fit accuracy | Helped |
| Weight skin-cloth probability outside the robust loss instead of inside it (ablation) | SMPL-X scan fitting · 100 scans | skin error: 4.82mm -> 4.73mm | No clear effect |
| Weight skin-cloth probability outside the robust loss instead of inside it (ablation) | SMPL-X scan fitting · 100 scans | cloth error: 4.51mm -> 4.42mm | No clear effect |
Closest papers by meaning
- FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions (CVPR 2024 · similarity 0.87)
- Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation (NeurIPS 2024 · similarity 0.86)
- PoseGen: Learning to Generate 3D Human Pose Dataset with NeRF (AAAI 2024 · similarity 0.86)
- BEDLAM2.0: Synthetic humans and cameras in motion (NeurIPS 2025 · similarity 0.86)
- $\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation (NeurIPS 2024 · similarity 0.86)
- PICO: Reconstructing 3D People In Contact with Objects (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.