Research map / 3D vision / Human pose estimation
Hand PointNet: 3D Hand Pose Estimation Using Point Sets
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 |
|---|---|---|---|
| Normalize the point cloud using OBB instead of only centering and scaling (ablation) | Basic PointNet · NYU | mean error distance: 15.5mm -> 12.2mm | Helped |
| Normalize the point cloud using OBB instead of only centering and scaling (ablation) | Hierarchical PointNet · NYU | mean error distance: 13.6mm -> 10.8mm | Helped |
| Use hierarchical rather than basic PointNet (ablation) | Hand pose regression on NYU · NYU | mean error distance: 12.2mm -> 10.8mm | Helped |
| Increase sampled points from 512 to 1024 (ablation) | Basic PointNet hand pose regression · NYU | mean error distance: 13.1mm -> 12.2mm | Helped |
| Increase sampled points from 1024 to 2048 (ablation) | Basic PointNet hand pose regression · NYU | mean error distance: 12.2mm -> 12.0mm | No clear effect |
| Add fingertip refinement using neighboring points (ablation) | Hand PointNet · NYU | mean error distance | Helped |
| Add fingertip refinement using neighboring points (ablation) | Hand PointNet · MSRA | mean error distance | Helped |
| Add fingertip refinement using neighboring points (ablation) | Hand PointNet · ICVL | mean error distance | Helped |
Closest papers by meaning
- Two Heads Are Better than One: Image-Point Cloud Network for Depth-Based 3D Hand Pose Estimation (AAAI 2023 · similarity 0.94)
- 3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation From Single Depth Images (CVPR 2017 · similarity 0.93)
- 3D Hand Shape and Pose Estimation From a Single RGB Image (CVPR 2019 · similarity 0.92)
- Point-To-Pose Voting Based Hand Pose Estimation Using Residual Permutation Equivariant Layer (CVPR 2019 · similarity 0.91)
- DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed With Deep Features (CVPR 2016 · similarity 0.91)
- Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals (CVPR 2018 · similarity 0.90)
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.