- Notifications
You must be signed in to change notification settings - Fork85
Project repo for Learning Category-Specific Mesh Reconstruction from Image Collections
License
NotificationsYou must be signed in to change notification settings
akanazawa/cmr
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Angjoo Kanazawa*, Shubham Tulsiani*, Alexei A. Efros, Jitendra Malik
University of California, BerkeleyIn ECCV, 2018
This code is no longer actively maintained. For pytorch 1.x, python3, and pytorch NMR support, please seethis implementation fromchenyuntc.
- Python 2.7
- PyTorch tested on version
0.3.0.post4
virtualenv venv_cmrsource venv_cmr/bin/activatepip install -U pipdeactivatesource venv_cmr/bin/activatepip install -r requirements.txtcd external;bash install_external.sh- From the
cmrdirectory, download the trained model:
wget https://people.eecs.berkeley.edu/~kanazawa/cachedir/cmr/model.tar.gz & tar -vzxf model.tar.gzYou should seecmr/cachedir/snapshots/bird_net/
- Run the demo:
python -m cmr.demo --name bird_net --num_train_epoch 500 --img_path cmr/demo_data/img1.jpgpython -m cmr.demo --name bird_net --num_train_epoch 500 --img_path cmr/demo_data/birdie.jpgPlease seedoc/train.md
If you use this code for your research, please consider citing:
@inProceedings{cmrKanazawa18, title={Learning Category-Specific Mesh Reconstruction from Image Collections}, author = {Angjoo Kanazawa and Shubham Tulsiani and Alexei A. Efros and Jitendra Malik}, booktitle={ECCV}, year={2018}}