Research map / 3D vision / Human pose estimation
DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed With Deep Features
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 Gaussian noise to synthetic depth maps during training (ablation) | DeepHand global rotation classifier · Real hand depth sequence | classification accuracy: 44.88% -> 77.00% | Helped |
| use hierarchical global-to-local pose estimation instead of holistic estimation (ablation) | DeepHand · Synthetic hand pose sequences | pose error | Helped |
| estimate pose from a pool of activation features rather than a single nearest feature (ablation) | DeepHand · Synthetic hand pose sequences | pose error | Helped |
| add temporal neighbors from previous frames to matrix completion (ablation) | DeepHand · Synthetic hand pose sequences | pose error | Helped |
| kernelize the feature matrix (ablation) | DeepHand matrix completion · Synthetic hand pose sequences | pose error | Helped |
| use matrix completion instead of similarity-weighted regression (ablation) | DeepHand · Synthetic hand pose sequences | pose error | Helped |
| directly regress joint angles with a ConvNet (ablation) | DeepHand · Synthetic hand pose sequences | joint angle error | Hurt |
| use PCA instead of the ConvNet activation features for global pose initialization (ablation) | DeepHand global pose initialization · Global rotation classification | accuracy: 5.72% versus 72.30 % | Hurt |
Closest papers by meaning
- Self-Supervised 3D Hand Pose Estimation Through Training by Fitting (CVPR 2019 · similarity 0.93)
- 3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation From Single Depth Images (CVPR 2017 · similarity 0.93)
- Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals (CVPR 2018 · similarity 0.92)
- Robust 3D Hand Pose Estimation in Single Depth Images: From Single-View CNN to Multi-View CNNs (CVPR 2016 · similarity 0.92)
- Crossing Nets: Combining GANs and VAEs With a Shared Latent Space for Hand Pose Estimation (CVPR 2017 · similarity 0.92)
- SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training (ICLR 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.