Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/Lotayou/densebody_pytorch

PyTorch implementation of CloudWalk's recent work DenseBody
https://github.com/Lotayou/densebody_pytorch

3d-reconstruction human pose-estimation pytorch

Last synced: about 2 months ago
JSON representation

PyTorch implementation of CloudWalk's recent work DenseBody

Host: GitHub
URL: https://github.com/Lotayou/densebody_pytorch
Owner: Lotayou
License: gpl-3.0
Created: 2019-03-29T07:38:37.000Z (almost 6 years ago)
Default Branch: master
Last Pushed: 2019-08-26T03:22:27.000Z (over 5 years ago)
Last Synced: 2024-08-01T13:32:45.275Z (5 months ago)
Topics: 3d-reconstruction, human, pose-estimation, pytorch
Language: Python
Homepage: https://arxiv.org/pdf/1903.10153.pdf
Size: 3.97 MB
Stars: 413
Watchers: 21
Forks: 71
Open Issues: 13
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

        # densebody_pytorch

PyTorch implementation of CloudWalk's recent paper [DenseBody](https://arxiv.org/abs/1903.10153v3).

**Note**: For most recent updates, please check out the `dev` branch.

**Update on 20190613** A toy dataset has been released to facilitate the reproduction of this project. checkout [`PREPS.md`](PREPS.md) for details.

**Update on 20190826** A pre-trained model ([Encoder](https://yadi.sk/d/isvVFGIU6cHueQ)/[Decoder](https://yadi.sk/d/ck-JBue4XYNpHQ)) has been released to facilitate the reproduction of this project. 

![paper teaser](teaser/teaser.jpg)

### Reproduction results

Here is the reproduction result (left: input image; middle: ground truth UV position map; right: estimated UV position map)



  



### Update Notes

- SMPL official UV map is now supported! Please checkout [`PREPS.md`](PREPS.md) for details.

- Code reformating complete! Please refer to `data_utils/UV_map_generator.py` for more details.

- Thanks [Raj Advani](https://github.com/radvani) for providing new hand crafted UV maps!

### Training Guidelines

Please follow the instructions [`PREPS.md`](PREPS.md) to prepare your training dataset and UV maps. Then run `train.sh` or `nohup_train.sh` to begin training. 

### Customizations

To train with your own UV map, checkout [`UV_MAPS.md`](UV_MAPS.md) for detailed instructions.

To explore different network architectures, checkout [`NETWORKS.md`](NETWORKS.md) for detailed instructions.

### TODO List

- [x] Creating ground truth UV position maps for Human36m dataset.

    - [x] [20190329]() Finish UV data processing.

    - [x] [20190331]() Align SMPL mesh with input image.

    - [x] [20190404]() Data washing: Image resize to 256*256 and 2D annotation compensation.

    - [x] [20190411]() Generate and save UV position map.

        - [x] [radvani](https://github.com/radvani) Hand parsed new 3D UV data

        - [x] Validity checked with minor artifacts (see results below)

        - [x] Making UV_map generation module a separate class.

    - [x] [20190413]() Prepare ground truth UV maps for washed dataset.

    - [x] [20190417]() SMPL official UV map supported!

    - [x] [20190613]() A testing toy dataset has been released!

    

- [x] Prepare baseline model training

    - [x] [20190414]() Network design, configs, trainer and dataloader

    - [x] [20190414]() Baseline complete with first-hand results. Something issue still needs to be addressed.

    - [x] [20190420]() Testing with different UV maps.

### Authors

**[Lingbo Yang(Lotayou)](https://github.com/Lotayou)**: The owner and maintainer of this repo.

**[Raj Advani(radvani)](https://github.com/radvani)**: Provide several hand-crafted UV maps and many constructive feedbacks.

### Citation

Please consider citing the following paper if you find this project useful.

[DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image](https://arxiv.org/abs/1903.10153v3)

### Acknowledgements

The network training part is inspired by [BicycleGAN](https://github.com/junyanz/BicycleGAN)