https://github.com/maudzung/3d-human-pose-estimation
An implementation of 3D human pose estimation based on 2D keypoints in images
https://github.com/maudzung/3d-human-pose-estimation
2d-keypoints 3dposeestimation human-pose-estimation human36m
Last synced: 7 months ago
JSON representation
An implementation of 3D human pose estimation based on 2D keypoints in images
- Host: GitHub
- URL: https://github.com/maudzung/3d-human-pose-estimation
- Owner: maudzung
- Created: 2020-03-16T08:46:11.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2020-03-16T08:46:18.000Z (about 5 years ago)
- Last Synced: 2023-03-04T23:25:11.775Z (over 2 years ago)
- Topics: 2d-keypoints, 3dposeestimation, human-pose-estimation, human36m
- Language: Jupyter Notebook
- Size: 724 KB
- Stars: 6
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
An implementation of 3D Human Pose Estimation using 2D keypoints in images
**Folder structure**
```
${ROOT}
├──checkpoints/
├──datasets/
├──human36m_preprocessing/
├──logs/
├──src/
├──config/
├──data_process/
├──evaluation/
├──losses/
├──models/
├──notebooks/
├──train/
├──utils/
├──README.md
```
# To-do-list
- [x] Pre-process the dataset
- [x] Using 2D keypoints as the input of DNN to estimate 3D HPE