Research map / 3D vision / Human pose estimation
3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation From Single Depth Images
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 3D CNN with projective D-TSDF and 3D data augmentation | single-image hand pose estimation · MSRA dataset | proportion of good frames: about 10%, 12%, 25% and 30% higher | Helped |
| use 3D CNN with projective D-TSDF and 3D data augmentation | single-image hand pose estimation · NYU dataset | proportion of good frames: about 10% more | Helped |
| use 3D CNN with projective D-TSDF and 3D data augmentation | single-image hand pose estimation · NYU dataset | proportion of joints within error threshold: about 10% more | Helped |
| replace a 32×32×32 volume with a 16×16×16 volume (ablation) | 3D CNN · MSRA dataset | pose estimation accuracy | Hurt |
| replace a 32×32×32 volume with a 64×64×64 volume (ablation) | 3D CNN · MSRA dataset | pose estimation accuracy | No clear effect |
| use projective TSDF instead of projective D-TSDF (ablation) | 3D CNN · MSRA dataset | pose estimation accuracy | Hurt |
| use accurate TSDF instead of projective D-TSDF (ablation) | 3D CNN · MSRA dataset | pose estimation accuracy | Hurt |
| add 3D data augmentation (ablation) | 3D CNN with projective D-TSDF · MSRA dataset | pose estimation accuracy | Helped |
Closest papers by meaning
- Hand PointNet: 3D Hand Pose Estimation Using Point Sets (CVPR 2018 · similarity 0.93)
- Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals (CVPR 2018 · similarity 0.93)
- 3D Hand Shape and Pose Estimation From a Single RGB Image (CVPR 2019 · similarity 0.93)
- DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed With Deep Features (CVPR 2016 · similarity 0.93)
- Robust 3D Hand Pose Estimation in Single Depth Images: From Single-View CNN to Multi-View CNNs (CVPR 2016 · similarity 0.92)
- Reconstructing Hands in 3D with Transformers (CVPR 2024 · 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.