Research map / 3D vision / Human pose estimation
3D Hand Shape and Pose From Images in the Wild
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 |
|---|---|---|---|
| Add 2D joint heat-maps to RGB input (ablation) | Ours · Stereo | average 3D joint distance (mm): 9.76 -> 10.18 | Hurt |
| Use 2D joint heat-maps instead of RGB input (ablation) | Ours · Stereo | average 3D joint distance (mm): 9.76 -> 10.46 | Hurt |
| Add 2D joint heat-maps to RGB input (ablation) | Ours · Dexter+Object | average 3D joint distance (mm): 33.16 -> 25.53 | Helped |
| Use 2D joint heat-maps instead of RGB input (ablation) | Ours · Dexter+Object | average 3D joint distance (mm): 33.16 -> 25.93 | Helped |
| Add 2D joint heat-maps to RGB input (ablation) | Ours · EgoDexter | average 3D joint distance (mm): 51.87 -> 45.58 | Helped |
| Use 2D joint heat-maps instead of RGB input (ablation) | Ours · EgoDexter | average 3D joint distance (mm): 51.87 -> 45.33 | Helped |
| Add 2D joint heat-maps to RGB input (ablation) | Ours · Mpii+Nzsl test | average re-projected 2D joint distance (px): 23.04 -> 18.95 | Helped |
| Use 2D joint heat-maps instead of RGB input (ablation) | Ours · Mpii+Nzsl test | average re-projected 2D joint distance (px): 23.04 -> 20.65 | Helped |
| Predict hand parameters from RGB and decode them with a fixed MANO hand model rather than fitting only 2D detections | Ours RGB vs 2D fit · Stereo | average 3D joint distance (mm): 23.21 -> 9.76 | Helped |
Closest papers by meaning
- 3D Hand Shape and Pose Estimation From a Single RGB Image (CVPR 2019 · similarity 0.93)
- 3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation From Single Depth Images (CVPR 2017 · similarity 0.91)
- HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation From a Single Depth Map (CVPR 2020 · similarity 0.91)
- Reconstructing Hands in 3D with Transformers (CVPR 2024 · similarity 0.90)
- SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training (ICLR 2025 · similarity 0.89)
- SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes (NeurIPS 2025 · similarity 0.89)
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.