Introduction

This repository contains the code for the paper Non-Rigid Shape Registration via Deep Functional Maps Prior

This code is under construction. The final version of code will be released soon.

Installation

To install requirements:

pip install -r requirements.txt

Installing PyTorch may require an ad hoc procedure, depending on your computer settings.

Training

In the DFM folder, run the following command to train our modified DGCNN model on the train set:

python train.py

Evaluation

In the registration folder, run the following command to evaluate the trained model on the test set:

python test.py

the results will be saved in the results folder.

License

If you use this code, please cite our paper.

@inproceedings{NEURIPS2023_b654d615,
 author = {Jiang, Puhua and Sun, Mingze and Huang, Ruqi},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {A. Oh and T. Neumann and A. Globerson and K. Saenko and M. Hardt and S. Levine},
 pages = {58409--58427},
 publisher = {Curran Associates, Inc.},
 title = {Non-Rigid Shape Registration via Deep Functional Maps Prior},
 url = {https://proceedings.neurips.cc/paper_files/paper/2023/file/b654d6150630a5ba5df7a55621390daf-Paper-Conference.pdf},
 volume = {36},
 year = {2023}
}

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. For any commercial uses or derivatives, please contact us.

rqhuang88 / DFR