Research map / 3D vision / Human pose estimation
Augmented Skeleton Space Transfer for Depth-Based Hand Pose 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 |
|---|---|---|---|
| Add skeleton-space augmentation and the unified HPG-HPE framework | HPE baseline · Big Hand 2.2M | HPE error (mm): 17.1 -> 13.7 | Helped |
| Add skeleton-space augmentation and the unified HPG-HPE framework | HPE baseline · ICVL | HPE error (mm): 12.1 -> 8.5 | Helped |
| Add skeleton-space augmentation and the unified HPG-HPE framework | HPE baseline · MSRA | HPE error (mm): 16.3 -> 12.5 | Helped |
| Add skeleton-space augmentation and the unified HPG-HPE framework | HPE baseline · NYU | HPE error (mm): 17.3 -> 14.1 | Helped |
| Jointly train HPG and HPE rather than training them independently (ablation) | HPG · Big Hand 2.2M | HPG error: 0.151 -> 0.124 | Helped |
| Add skeleton augmentation during joint HPG-HPE training (ablation) | HPG · Big Hand 2.2M | HPG error: 0.124 -> 0.102 | Helped |
| Add skeleton augmentation to training (ablation) | HPE · Big Hand 2.2M | HPE error (mm): 15.7 -> 14.1 | Helped |
| Add test-time refinement guided by HPG and HPDY (ablation) | HPE · Big Hand 2.2M | HPE error (mm): 14.1 -> 13.7 | Helped |
| Add test-time refinement guided by HPG and HPDY (ablation) | HPE · ICVL | HPE error (mm): 9.1 -> 8.5 | Helped |
| Add test-time refinement guided by HPG and HPDY (ablation) | HPE · MSRA | HPE error (mm): 13.1 -> 12.5 | Helped |
| Add test-time refinement guided by HPG and HPDY (ablation) | HPE · NYU | HPE error (mm): 14.9 -> 14.1 | Helped |
| Increase skeleton augmentation from 5× to 10× (ablation) | AST without refinement · Big Hand 2.2M | HPE error (mm): 15.1 -> 14.1 | Helped |
Closest papers by meaning
- V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation From a Single Depth Map (CVPR 2018 · similarity 0.90)
- Crossing Nets: Combining GANs and VAEs With a Shared Latent Space for Hand Pose Estimation (CVPR 2017 · similarity 0.90)
- Dense 3D Regression for Hand Pose Estimation (CVPR 2018 · similarity 0.90)
- BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysis (CVPR 2017 · similarity 0.89)
- HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation From a Single Depth Map (CVPR 2020 · similarity 0.89)
- Reconstructing Hands in 3D with Transformers (CVPR 2024 · 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.