84
GitHub - akanazawa/cmr: Project repo for Learning Category-Specific Mesh Reconst...
source link: https://github.com/akanazawa/cmr
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
README.md
Learning Category-Specific Mesh Reconstruction from Image Collections
Angjoo Kanazawa*, Shubham Tulsiani*, Alexei A. Efros, Jitendra Malik
University of California, Berkeley
Requirements
- Python 2.7
- PyTorch tested on version
0.3.0.post4
Installation
Setup virtualenv
virtualenv venv_cmr
source venv_cmr/bin/activate
pip install -U pip
deactivate
source venv_cmr/bin/activate
pip install -r requirements.txt
Install Neural Mesh Renderer and Perceptual loss
cd external;
bash install_external.sh
Demo
- From the
cmr
directory, download the trained model:
wget https://people.eecs.berkeley.edu/~kanazawa/cachedir/cmr/model.tar.gz & tar -vzxf model.tar.gz
You should see cmr/cachedir/snapshots/bird_net/
- Run the demo:
python -m cmr.demo --name bird_net --num_train_epoch 500 --img_path cmr/demo_data/img1.jpg
python -m cmr.demo --name bird_net --num_train_epoch 500 --img_path cmr/demo_data/birdie.jpg
Training
Please see doc/train.md
Citation
If you use this code for your research, please consider citing:
@article{cmrKanazawa18,
title={Learning Category-Specific Mesh Reconstruction
from Image Collections},
author = {Angjoo Kanazawa and
Shubham Tulsiani
and Alexei A. Efros
and Jitendra Malik},
journal={arXiv preprint arXiv:1803.07549},
year={2018}
}
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK