Research map / 3D vision / Human pose estimation
Crossing Nets: Combining GANs and VAEs With a Shared Latent Space for Hand Pose Estimation
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 |
|---|---|---|---|
| jointly train the generator and discriminator using synthesized and unlabeled depth maps | Crossing Nets · NYU, MSRA, and ICVL | mean joint error | Helped |
| pretrain the discriminator's first two convolutional layers with a GAN | posterior estimation · Semi-supervised hand pose estimation, 2% labeled data | mean joint error | Helped |
| pretrain the discriminator's first two convolutional layers with a GAN | posterior estimation · Semi-supervised hand pose estimation, at least 5% labeled data | mean joint error | No clear effect |
| add the smoothness task (ablation) | Crossing Nets · Hand pose estimation | mean joint error | Helped |
| add the GAN disambiguation task (ablation) | Crossing Nets · Hand pose estimation | mean joint error | Helped |
| use a holistic estimator rather than a hierarchical estimator | Crossing Nets · MSRA, error thresholds 10–30mm | percentage of frames below error threshold | Hurt |
| use a holistic estimator rather than a hierarchical estimator | Crossing Nets · MSRA, error thresholds larger than 35mm | percentage of frames below error threshold | Helped |
| use Crossing Nets instead of deepPrior | Crossing Nets · ICVL, error thresholds at least 20mm | percentage of frames below error threshold | Helped |
| use Crossing Nets instead of refinement | Crossing Nets · ICVL, error thresholds at least 30mm | percentage of frames below error threshold: 2% | Helped |
Closest papers by meaning
- DeepHand: Robust Hand Pose Estimation by Completing a Matrix Imputed With Deep Features (CVPR 2016 · similarity 0.92)
- Self-Supervised 3D Hand Pose Estimation Through Training by Fitting (CVPR 2019 · similarity 0.92)
- Robust 3D Hand Pose Estimation in Single Depth Images: From Single-View CNN to Multi-View CNNs (CVPR 2016 · similarity 0.91)
- Cross-Modal Deep Variational Hand Pose Estimation (CVPR 2018 · similarity 0.91)
- 3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation From Single Depth Images (CVPR 2017 · similarity 0.91)
- Weakly-Supervised Domain Adaptation via GAN and Mesh Model for Estimating 3D Hand Poses Interacting Objects (CVPR 2020 · similarity 0.91)
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.