Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/pvnieo/geomfmaps_pytorch
A minimalist pytorch implementation of: "Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence"
https://github.com/pvnieo/geomfmaps_pytorch
feature-extraction functional-maps python3 pytorch shape-correspondence shape-descriptor shape-matching
Last synced: 13 days ago
JSON representation
A minimalist pytorch implementation of: "Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence"
- Host: GitHub
- URL: https://github.com/pvnieo/geomfmaps_pytorch
- Owner: pvnieo
- License: mit
- Created: 2020-09-28T22:31:50.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2023-12-26T21:10:54.000Z (about 1 year ago)
- Last Synced: 2024-08-27T14:16:49.798Z (4 months ago)
- Topics: feature-extraction, functional-maps, python3, pytorch, shape-correspondence, shape-descriptor, shape-matching
- Language: Python
- Homepage:
- Size: 13.7 KB
- Stars: 24
- Watchers: 3
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[](https://arxiv.org/pdf/2003.14286.pdf)
:warning: :rotating_light: this code base is no longer maintained :confused:
# GeomFmaps-pytorch
A minimalist pytorch implementation of: "Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence" [[1]](#bookmark-references), appeared in [CVPR 2020](http://cvpr2020.thecvf.com/).
## Installation
This implementation runs on python >= 3.7, use pip to install dependencies:
```
pip3 install -r requirements.txt
```
## Download data & preprocessing
The preprocessing code will be added later.
For the moment, we refer the reader to the [original implementation](https://github.com/LIX-shape-analysis/GeomFmaps) of GeomFmaps to download the data and the preprocessing code.
It should be noted that for each dataset (faust, scape, etc), this module expect that the dataset folder contains 3 folders:
* `off` folder: this folder contains the meshes
* `spectral` folder: this folder contains the laplace beltrami related data. It's composed from files having the same name as the `off` folder. Each fileis a `.mat` contaning a `dict` containing three keys: `evals`, `evecs` and `evecs_trans`. This files are created by the preprocessing code.
* `corres` folder: this folder contains the ".vts" files necessary for the calculation of the ground truth maps.
## Usage
Use the `config.yaml` file to specify the hyperparameters as well as the dataset to be used.
Use the `train.py` script to train the GeomFmaps model.
```
python3 train.py
```
References
---------------------
[1] [Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence](https://arxiv.org/pdf/2003.14286.pdf)