-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
582e297
commit ca10b0f
Showing
1 changed file
with
36 additions
and
6 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,18 +1,48 @@ | ||
# RAC: Reconstructing Animatable Categories from Videos | ||
|
||
[[Project page]](https://www.contrib.andrew.cmu.edu/~gengshay/rac-www/) [Paper] [Colab] | ||
**[[Project page]](https://gengshan-y.github.io/rac-www/)** | ||
|
||
This repo is currently under development. It will contain the pre-trained category models of cats, dogs, and human. | ||
![rac](https://user-images.githubusercontent.com/13134872/236699509-ee1569ba-28da-4e53-aedc-ff20cc19e87f.gif) | ||
|
||
See `demo.ipynb` for a interactive demo visualizing learned morphology and articulations. | ||
![Screenshot 2023-01-22 at 9 58 34 PM](https://user-images.githubusercontent.com/13134872/213958804-a78f2a17-bea6-46ac-8a9c-8e321ff4df44.png) | ||
|
||
### Updates | ||
- [05/07/2023] We plan to release an re-implementation of training code through [lab4d](https://github.com/lab4d-org/lab4d). | ||
- [01/22/2023] This repo is under development. It will contain the pre-trained category models of cats, dogs, and human. | ||
|
||
|
||
### Install | ||
``` | ||
git clone [email protected]:gengshan-y/rac.git --recursive | ||
cd rac | ||
# base dependencies | ||
conda env create -f misc/rac-cu113.yml | ||
# other dependencies | ||
conda activate rac-cu113 | ||
pip install git+https://github.com/facebookresearch/pytorch3d.git | ||
cd quaternion; python setup.py install; cd - | ||
``` | ||
|
||
## Pretrained models | ||
### Pretrained models | ||
``` | ||
# download optimized model | ||
# download model weights | ||
wget https://www.dropbox.com/sh/h1w82lb4rg48jui/AACD8q-DCFjyDhRx0-j7EjWLa -O tmp.zip | ||
mkdir -p logdir | ||
unzip tmp.zip -d ./logdir | ||
rm tmp.zip | ||
``` | ||
|
||
### Re-targeting | ||
``` | ||
python explore.py --flagfile logdir/dog80-v0/opts.log --nolineload --seqname dog80 --full_mesh --noce_color --svid 69 --tvid 45 | ||
``` | ||
retargets the source video 69 to target video 45. Results are saved at `logdir/dog80-v0/explore-motion-69.mp4`. | ||
|
||
https://user-images.githubusercontent.com/13134872/236701581-4b34131a-aee7-45b3-9b3e-63b4af4940e5.mp4 | ||
|
||
|
||
|
||
### Demo | ||
See `demo.ipynb` for an interactive demo visualizing learned morphology and articulations. | ||
![Screenshot 2023-01-22 at 9 58 34 PM](https://user-images.githubusercontent.com/13134872/213958804-a78f2a17-bea6-46ac-8a9c-8e321ff4df44.png) |