LSPS - GitLite

KO | EN

gitlite — search

#python #ai #llm #machine-learning #rust #deep-learning #linux #docker #nodejs #awesome #kubernetes #ios #openai #open-source

LSPS

(★ 61)

Source code for "3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space"

파일 탐색기

최종 버전 다운로드 (.zip)

- .DS_Store
- nicvl.yaml
- nnyu.yaml
- dis_icvl.gif
- dis_nyu.gif
- walk_icvl.gif
- walk_nyu.gif
- - .DS_Store
  - __init__.py
  - __init__.pyc
  - basetypes.py
  - basetypes.pyc
  - dataset.py
  - dataset.pyc
  - dataset_hand2.py
  - dataset_hand2.pyc
  - importers.py
  - importers.pyc
  - transformations.py
  - transformations.pyc
- - __init__.py
  - __init__.pyc
  - common_net.py
  - common_net.pyc
  - helpers.py
  - helpers.pyc
  - init.py
  - init.pyc
  - lsps_nets.py
  - lsps_nets.pyc
  - lsps_trainer.py
  - lsps_trainer.pyc
- - __init__.py
  - __init__.pyc
  - evaluation.py
  - evaluation.pyc
  - handdetector.py
  - handdetector.pyc
  - handpose_evaluation.py
  - handpose_evaluation.pyc
  - helpers.py
  - helpers.pyc
  - net_config.py
  - net_config.pyc
  - util.py
  - util.pyc
  - util2.py
  - util_old.py
- .DS_Store
- __init__.py
- common.py
- common.pyc
- depth_train.py
- pose_train.py
.DS_Store
LICENSE
README.md
Youtube.png

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

Code for our BMVC oral paper (4.3% acceptance rate): "3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space"  see the paper at https://arxiv.org/abs/1807.05380

### Citation

If you found this research useful, please cite:

```
@article{abdi20183d,
title={3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space},
      author={Abdi, Masoud and Abbasnejad, Ehsan and Lim, Chee Peng and Nahavandi, Saeid},
      journal={arXiv preprint arXiv:1807.05380},
      year={2018}
}
```

## Supplementary Video:
### Real-time 3d hand pose estimation on CPU
[![](https://raw.githubusercontent.com/masabdi/LSPS/master/Youtube.png)](https://youtu.be/Hjkob3dV-kY)

## Discriminative Results:
![Alt text](https://raw.githubusercontent.com/masabdi/LSPS/master/img/dis_icvl.gif)

## Generative Results:
![Alt text](https://raw.githubusercontent.com/masabdi/LSPS/master/img/walk_nyu.gif)

#  Usage
1. Use pose_train to train the vae: 
```
python depth_train.py --config ../exps/nnyu.yaml
```

2. Pretrain the depth model using: 
```
python depth_train.py --config ../exps/nnyu.yaml --mode pretrain
```

3. Finally run this command for the unsupervised setting: 
```
python depth_train.py --config ../exps/nnyu.yaml --mode estimate3
```