Research map / 3D vision / Human pose estimation
Self-Supervised 3D Hand Pose Estimation Through Training by Fitting
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 multi-view consistency and cross-view fitting (ablation) | Self-Supervised 3D Hand Pose Estimation Through Training by Fitting · NYU Hand Pose Dataset testing set | mean joint error: 17.79mm -> 12.62mm | Helped |
| Add the VAE prior loss (ablation) | Self-Supervised 3D Hand Pose Estimation Through Training by Fitting · NYU Hand Pose Dataset testing set | mean joint error: 14.17mm -> 12.62 mm | Helped |
| Add the bone length prior loss (ablation) | Self-Supervised 3D Hand Pose Estimation Through Training by Fitting · NYU Hand Pose Dataset testing set | mean joint error: 14.56mm -> 12.62 mm | Helped |
| Add the collision prior loss (ablation) | Self-Supervised 3D Hand Pose Estimation Through Training by Fitting · NYU Hand Pose Dataset testing set | mean joint error: 13.73mm -> 12.62 mm | Helped |
| Add random noise augmentation to synthesized depth maps (ablation) | Synthesized-data initialization · NYU Hand Pose Dataset testing set | mean joint error: 27.85mm -> 22.65mm | Helped |
| Add single-view training data to the multi-view half (ablation) | Self-Supervised 3D Hand Pose Estimation Through Training by Fitting · NYU Hand Pose Dataset testing set | mean joint error: 13.77mm -> 13.33mm | Helped |
| Add training samples to the test-sample training set (ablation) | Self-Supervised 3D Hand Pose Estimation Through Training by Fitting · NYU Hand Pose Dataset testing set | mean joint error: 14.53mm -> 12.31mm | Helped |
| Replace synthetic-only training with self-supervised fine-tuning on real depth maps | Self-Supervised 3D Hand Pose Estimation Through Training by Fitting · NYU Hand Pose Dataset testing set | mean joint error: 22.65mm -> 12.62 mm | Helped |
Closest papers by meaning
- DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed With Deep Features (CVPR 2016 · similarity 0.93)
- Dense 3D Regression for Hand Pose Estimation (CVPR 2018 · similarity 0.92)
- Crossing Nets: Combining GANs and VAEs With a Shared Latent Space for Hand Pose Estimation (CVPR 2017 · similarity 0.92)
- Efficiently Creating 3D Training Data for Fine Hand Pose Estimation (CVPR 2016 · 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)
- Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals (CVPR 2018 · similarity 0.92)
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.