Research map / 3D vision / Human pose estimation
Monocular Real-Time Hand Shape and Motion Capture Using Multi-Modal Data
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 |
|---|---|---|---|
| Use the proposed multimodal training and hand-capture architecture | Monocular hand pose and shape capture · Dexter+Object (DO) | AUC of PCK: .825 -> .948 | Helped |
| Use the proposed multimodal training and hand-capture architecture | Monocular hand pose and shape capture · EgoDexter (ED) | AUC of PCK: .674 -> .811 | Helped |
| Add IKNet for pose-prior-based rotation recovery (ablation) | DetNet hand joint prediction · Dexter+Object (DO) | AUC of PCK: .923 -> .948 | Helped |
| Add IKNet for pose-prior-based rotation recovery (ablation) | DetNet hand joint prediction · EgoDexter (ED) | AUC of PCK: .804 -> .811 | Helped |
| Add IKNet for pose-prior-based rotation recovery (ablation) | DetNet hand joint prediction · STB | AUC of PCK: .891 -> .898 | Helped |
| Add direct rotational supervision using Ll2 and Lcos (ablation) | IKNet · Dexter+Object (DO) | AUC of PCK: .933 -> .948 | Helped |
| Add direct rotational supervision using Ll2 and Lcos (ablation) | IKNet · EgoDexter (ED) | AUC of PCK: .823 -> .811 | No clear effect |
| Add direct rotational supervision using Ll2 and Lcos (ablation) | IKNet · STB | AUC of PCK: .869 -> .898 | Helped |
| Add weak supervision from 3DPosData (ablation) | IKNet · Dexter+Object (DO) | AUC of PCK: .926 -> .948 | Helped |
| Add weak supervision from 3DPosData (ablation) | IKNet · EgoDexter (ED) | AUC of PCK: .809 -> .811 | Helped |
| Add weak supervision from 3DPosData (ablation) | IKNet · STB | AUC of PCK: .873 -> .898 | Helped |
| Add quaternion L2 loss Ll2 (ablation) | IKNet · Dexter+Object (DO) | AUC of PCK: .943 -> .948 | Helped |
Closest papers by meaning
- Efficiently Creating 3D Training Data for Fine Hand Pose Estimation (CVPR 2016 · similarity 0.89)
- Spatial-Temporal Parallel Transformer for Arm-Hand Dynamic Estimation (CVPR 2022 · similarity 0.89)
- Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation (AAAI 2024 · similarity 0.87)
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.87)
- Monocular 3D Hand Mesh Recovery via Dual Noise Estimation (AAAI 2024 · similarity 0.87)
- SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes (NeurIPS 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.