AtlasNet V2 - Learning Elementary Structures
This work was build upon Thibault Groueix's AtlasNet and 3D-CODED projects. (you might want to have a look at those)
This repository contains the source codes for the paper AtlasNet V2 - Learning Elementary Structures.
Citing this work
If you find this work useful in your research, please consider citing:
@inproceedings{deprelle2019learning,
title={Learning elementary structures for 3D shape generation and matching},
author={Deprelle, Theo and Groueix, Thibault and Fisher, Matthew and Kim, Vladimir and Russell, Bryan and Aubry, Mathieu},
booktitle={Advances in Neural Information Processing Systems},
pages={7433--7443},
year={2019}
}
Project Page
The project page is available http://imagine.enpc.fr/~deprellt/atlasnet2/
Install
Clone the repo and install dependencies
This implementation uses Pytorch.
## Download the repository
git clone https://github.com/TheoDEPRELLE/AtlasNetV2.git
cd AtlasNetV2
## Create python env with relevant packages
conda create --name atlasnetV2 python=3.7
source activate atlasnetV2
pip install pandas visdom
conda install pytorch torchvision -c pytorch
conda install -c conda-forge matplotlib
# you're done ! Congrats :)
Training
Data
cd data; ./download_data.sh; cd ..
We used the ShapeNet dataset for 3D models.
When using the provided data make sure to respect the shapenet license.
- The point clouds from ShapeNet, with normals go in
data/customShapeNet - The corresponding normalized mesh (for the metro distance) goes in
data/ShapeNetCorev2Normalized - the rendered views go in
data/ShapeNetRendering
The trained models and some corresponding results are also available online :
- The trained_models go in
trained_models/
Build chamfer distance
The chamfer loss is based on a custom cuda code that need to be compile.
source activate pytorch-atlasnet
cd ./extension
python setup.py install
Start training
- First launch a visdom server :
python -m visdom.server -p 8888
- Check out all the options :
git pull; python training/train.py --help
- Run the baseline :
git pull; python training/train.py --model AtlasNet --adjust mlp
git pull; python training/train.py --model AtlasNet --adjust linear
- Run the Patch Deformation module with the different adjustment modules :
git pull; python training/train.py --model PatchDeformation --adjust mlp
git pull; python training/train.py --model PatchDeformation --adjust linear
- Run the Point Translation module with the different adjustment modules:
git pull; python training/train.py --model PointTranslation --adjust mlp
git pull; python training/train.py --model PointTranslation --adjust linear
- Monitor your training on http://localhost:8888/
Models
The models train on the SURREAL dataset for the FAUST competition can be found here
Acknowledgement
This work was partly supported by ANR project EnHerit ANR-17-CE23-0008, Labex Bezout, and gifts from Adobe to Ecole des Ponts.
Here, it is said that the reconstruction task is evaluated by chamfer distance. But for surreal data, the ground-truth correspondences are known. Why not just compute the L2 distance for correponding points?
19 Dec 01, 2022
883 Jan 07, 2023
68 Dec 23, 2022
5 Oct 20, 2022
66 Jun 29, 2022
123 Jan 06, 2023
21 Jan 02, 2022
66 Dec 15, 2022
22 Nov 08, 2022
18 Dec 14, 2022
87 Dec 06, 2022
255 Sep 07, 2022
111 Dec 11, 2022
9 Aug 04, 2022
6 Nov 14, 2022
1 Nov 10, 2021
229 Jan 02, 2023
3.6k Jan 08, 2023
118 Jan 05, 2023
34 Sep 10, 2022