8000 GitHub - orenkatzir/VN-SPD: Shape-Pose Disentanglement using SE (3)-equivariant Vector Neurons
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Shape-Pose Disentanglement using SE (3)-equivariant Vector Neurons

Notifications You must be signed in to change notification settings

orenkatzir/VN-SPD

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Shape-Pose Disentanglement using SE(3)-equivariant Vector Neurons

[Project] [Paper]

This repository includes implementations to the method presented in the paper "Shape-Pose Disentanglement using SE(3)-equivariant Vector Neurons", including additional support for losses types and architectures (see code).

Data Preparation

We use the ShapeNet dataset as in AtlasNetV2. Please follow the instructions at CanonicalCapsules to convert the data to h5 files. Other datasets will be supported shortly.

Installation

The Dockerfile and the requirements.txt file include all the required dependencies. Please build and run it.

git clone VNT 
cd VNT
docker build -f Dockerfile -t vnt --build-arg USER_ID=$(id -u) --build-arg GROUP_ID=$(id -g)
docker run -t -d --gpus all -v ${PWD}:/app/VNT --name vnt_experiment -p 8097:8097 vnt

Execute the running container:

docker exec -it vnt_experiment /bin/bash
cd VNT

Usage

Training

To view training results and loss plots, run

python -m visdom.server

and click the URL http://localhost:8097/

Once visdom is up, start training

python train.py --model shape_pose --name chairs_paper --dataroot datasets/shapenet --class_choice chair --add_noise --apply_can_rot_loss --remove_knn 100 --resample --fps

An improved version of defaults can be seen in shape_pose2 model:

python train.py --model shape_pose2 --name chairs_updated --dataroot datasets/shapenet --class_choice chair --add_noise --apply_can_rot_loss --remove_knn 100 --resample --fps

Evaluation

python test.py --model shape_pose --name chairs_paper --dataroot datasets/shapenet --class_choice chair

or

python test.py --model shape_pose2 --name chairs_updated --dataroot datasets/shapenet --class_choice chair

Pre-trained model can be found here

Download the models and place the extracted folder under the checkpoints directory.

Citation

@article{katzir2022shape,
  title={Shape-Pose Disentanglement using SE (3)-equivariant Vector Neurons},
  author={Katzir, Oren and Lischinski, Dani and Cohen-Or, Daniel},
  journal={arXiv preprint arXiv:2204.01159},
  year={2022}
}

License

MIT License

Acknowledgement

The structure of this codebase is borrowed from the pytorch implementation of CycleGAN-pix2pix.

The code includes parts of the source code from VNN and AtlasNet2

About

Shape-Pose Disentanglement using SE (3)-equivariant Vector Neurons

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0