Research map / 3D vision / Human pose estimation
JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image
Linpu Fang, Xingyan Liu, Li Liu, Hang Xu, Wenxiong Kang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 the JGR (joint graph reasoning) module (ablation) | P2O + offset loss · NYU | Mean 3D error (mm): 10.54 -> 8.29 | Improved |
| add pixel-wise offset regression loss (ablation) | P2O baseline · NYU | Mean 3D error (mm): 10.83 -> 10.54 | Improved |
| use JGR instead of an attention module (ablation) | JGR-P2O · NYU | Mean 3D error (mm): 8.72 -> 8.29 | Improved |
| use P2O instead of the differentiable heat-map (DHM) module (ablation) | JGR-P2O · NYU | Mean 3D error (mm): 8.69 -> 8.29 | Improved |
| use skeleton graph instead of feature-similarity graph (ablation) | JGR module · NYU | Mean 3D error (mm): 8.45 -> 8.29 | Improved |
| use skeleton graph instead of parameterized-matrix graph (ablation) | JGR module · NYU | Mean 3D error (mm): 8.36 -> 8.29 | Improved |
| stack two hourglasses instead of one (ablation) | JGR-P2O · NYU | Mean 3D error (mm): 8.63 -> 8.29 | Improved |
| stack three hourglasses instead of two (ablation) | JGR-P2O · NYU | Mean 3D error (mm): 8.29 -> 8.27 | No clear effect |
Later papers that compared with this method
1 later accepted paper reports JGR-P2O as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeleton (ICCV 2021 · better on 2 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- V2V-PoseNet — V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation From a Single Depth Map (CVPR 2018) · better on 3 of 3 shared results
- CrossInfoNet — CrossInfoNet: Multi-Task Information Sharing Based Hand Pose Estimation (CVPR 2019) · better on 2 of 2 shared results
- HandPointNet — Hand PointNet: 3D Hand Pose Estimation Using Point Sets (CVPR 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Dense 3D Regression for Hand Pose Estimation (CVPR 2018 · similarity 0.90)
- Real-Time 3D Hand Pose Estimation with 3D Convolutional Neural Networks (TPAMI 2018 · similarity 0.90)
- V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation From a Single Depth Map (CVPR 2018 · similarity 0.90)
- 3D Hand Shape and Pose Estimation From a Single RGB Image (CVPR 2019 · similarity 0.90)
- 3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation From Single Depth Images (CVPR 2017 · similarity 0.90)
- Generalized Feedback Loop for Joint Hand-Object Pose Estimation (TPAMI 2019 · 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.
