Repository files navigation

Angjoo Kanazawa, Michael J. Black, David W. Jacobs, Jitendra MalikCVPR 2018

Project Page

• Python 2.7
• TensorFlow tested on version 1.3, demo alone runs with TF 1.12

virtualenv venv_hmrsource venv_hmr/bin/activatepip install -U pipdeactivatesource venv_hmr/bin/activatepip install -r requirements.txt

With GPU:

pip install tensorflow-gpu==1.3.0

Without GPU:

pip install tensorflow==1.3.0

This is only partialy tested.

conda env create -f hmr.yml

https://github.com/mattloper/chumpy/tree/db6eaf8c93eb5ae571eb054575fb6ecec62fd86d

1. Download the pre-trained models

wget https://people.eecs.berkeley.edu/~kanazawa/cachedir/hmr/models.tar.gz && tar -xf models.tar.gz

2. Run the demo

python -m demo --img_path data/coco1.pngpython -m demo --img_path data/im1954.jpg

Images should be tightly cropped, where the height of the person is roughly 150px.On images that are not tightly cropped, you can runopenpose and supplyits output json (run it with--write_json option).When json_path is specified, the demo will compute the right scale and bbox center to run HMR:

python -m demo --img_path data/random.jpg --json_path data/random_keypoints.json

(The demo only runs on the most confident bounding box, seesrc/util/openpose.py:get_bbox)

1. Download pre-trained models like above.
2. Run webcam Demo
3. Run the demo

python -m demo --img_path data/coco1.pngpython -m demo --img_path data/im1954.jpg

Please see thedoc/train.md!

If you use this code for your research, please consider citing:

@inProceedings{kanazawaHMR18,  title={End-to-end Recovery of Human Shape and Pose},  author = {Angjoo Kanazawa  and Michael J. Black  and David W. Jacobs  and Jitendra Malik},  booktitle={Computer Vision and Pattern Recognition (CVPR)},  year={2018}}

russoale has created a Python 3 version with TF 2.0:https://github.com/russoale/hmr2.0

Dawars has created a docker image for this project:https://hub.docker.com/r/dawars/hmr/

MandyMo has implemented a pytorch version of the repo:https://github.com/MandyMo/pytorch_HMR.git

Dene33 has made a .ipynb for Google Colab that takes video as input and returns .bvh animation!https://github.com/Dene33/video_to_bvh

layumi has added a 2D-to-3D color mapping function to the final obj:https://github.com/layumi/hmr

I have not tested them, but the contributions are super cool! Thank you!!Let me know if you have any mods that you would like to be added here!