Research map / 3D vision / Human pose estimation
Exploiting Learnable Joint Groups for Hand Pose Estimation
Moran Li, Yuan Gao, Nong Sang
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 learned joint grouping to the one-group baseline (ablation) | Hand pose estimation model · FreiHAND | Mean EPE [mm]: 0.932 -> 0.862 | Improved |
| Add feature fusion to the learned-group model (ablation) | Hand pose estimation model · FreiHAND | Mean EPE [mm]: 0.862 -> 0.856 | Improved |
| Ensemble checkpoints of the grouped, feature-fused method (ablation) | Hand pose estimation model · FreiHAND | Mean EPE [mm]: 0.856 -> 0.796 | Improved |
| Manually group joints into thumb, index, and other fingers (ablation) | Hand pose estimation model · RHD | Mean EPE [mm]: 11.534 -> 11.205 | Improved |
| Add feature fusion to manually grouped joints (ablation) | Hand pose estimation model · RHD | Mean EPE [mm]: 11.205 -> 11.021 | Improved |
| Use learned joint groups instead of one group (ablation) | Hand pose estimation model · RHD | Mean EPE [mm]: 11.534 -> 10.771 | Improved |
| Add feature fusion across learned groups (ablation) | Hand pose estimation model · RHD | Mean EPE [mm]: 10.771 -> 10.653 | Improved |
| Use 2 learned groups instead of one group (ablation) | Hand pose estimation model · RHD | Mean EPE: 11.534 -> 11.042 | Improved |
| Use 3 learned groups instead of one group (ablation) | Hand pose estimation model · RHD | Mean EPE: 11.534 -> 10.771 | Improved |
| Increase the learned group count from 3 to 4 (ablation) | Hand pose estimation model · RHD | Mean EPE: 10.771 -> 10.808 | No clear effect |
| Increase the learned group count from 3 to 5 (ablation) | Hand pose estimation model · RHD | Mean EPE: 10.771 -> 10.923 | No clear effect |
| Increase the learned group count from 3 to 21 (ablation) | Hand pose estimation model · RHD | Mean EPE: 10.771 -> 10.964 | No clear effect |
Closest papers by meaning
- Efficiently Creating 3D Training Data for Fine Hand Pose Estimation (CVPR 2016 · similarity 0.90)
- End-to-End Detection and Pose Estimation of Two Interacting Hands (ICCV 2021 · similarity 0.89)
- Dense 3D Regression for Hand Pose Estimation (CVPR 2018 · similarity 0.89)
- DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed With Deep Features (CVPR 2016 · similarity 0.89)
- Harmonious Feature Learning for Interactive Hand-Object Pose Estimation (CVPR 2023 · similarity 0.89)
- SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training (ICLR 2025 · similarity 0.88)
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.
