Research map / 3D vision / Human pose estimation
Cross-Domain 3D Hand Pose Estimation With Dual Modalities
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 |
|---|---|---|---|
| Use the dual-modality method instead of the strongest listed baseline | Cross-domain hand pose estimation · STB | PCK@0.05: 0.655 -> 0.775 | Helped |
| Use the dual-modality method instead of the strongest listed baseline | Cross-domain hand pose estimation · FreiHAND | PCK@0.05: 0.631 -> 0.658 | Helped |
| Use the dual-modality method instead of the strongest listed baseline | Cross-domain hand pose estimation · H3D | PCK@0.05: 0.720 -> 0.749 | Helped |
| Use the dual-modality method instead of the strongest listed baseline | Cross-domain hand pose estimation · MVHand | PCK@0.05: 0.640 -> 0.689 | Helped |
| Add depth-map supervision (ablation) | RGB-only supervised baseline · STB | EPE (mm): 19.66 -> 17.83 | Helped |
| Add attention-fused RGB supervision (ablation) | RGB and depth supervised model · STB | EPE (mm): 17.83 -> 16.92 | Helped |
| Add multi-modal contrastive learning (ablation) | Attention-fused supervised model · STB | EPE (mm): 16.92 -> 16.37 | Helped |
| Add pseudo-labeling (ablation) | Pre-trained multi-modal model · STB | EPE (mm): 16.37 -> 12.59 | Helped |
| Add self-distillation (ablation) | Pseudo-labeled model · STB | EPE (mm): 12.59 -> 11.99 | Helped |
| Add depth-map supervision (ablation) | RGB-only supervised baseline · FreiHAND | EPE (mm): 21.56 -> 20.14 | Helped |
| Add attention-fused RGB supervision (ablation) | RGB and depth supervised model · FreiHAND | EPE (mm): 20.14 -> 19.69 | Helped |
| Add multi-modal contrastive learning (ablation) | Attention-fused supervised model · FreiHAND | EPE (mm): 19.69 -> 19.19 | Helped |
Closest papers by meaning
- Cross-Modal Deep Variational Hand Pose Estimation (CVPR 2018 · similarity 0.93)
- Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation (AAAI 2024 · similarity 0.92)
- Efficiently Creating 3D Training Data for Fine Hand Pose Estimation (CVPR 2016 · similarity 0.90)
- 3D Hand Shape and Pose Estimation From a Single RGB Image (CVPR 2019 · similarity 0.89)
- Self-Supervised 3D Hand Pose Estimation Through Training by Fitting (CVPR 2019 · similarity 0.89)
- Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation (CVPR 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.