Unsupervised Contrastive Learning for Efficient and Robust Spectral Shape Matching (AAAI 2026)

Installation

conda create -n contrastivefmnet python=3.8 # create new viertual environment
conda activate contrastivefmnet
conda install pytorch cudatoolkit -c pytorch # install pytorch, cuda==11.8!
pip install -r requirements.txt # install other necessary libraries via pip

Dataset

To train and test datasets used in this paper, please download the datasets from DongliangCao and put all datasets under ../data/

├── data
    ├── FAUST_r
    ├── FAUST_a
    ├── SCAPE_r
    ├── SCAPE_a
    ├── SHREC19_r
    ├── TOPKIDS
    ├── SMAL_r
    ├── DT4D_r
    ├── SHREC20
    ├── SHREC16
    ├── SHREC16_test

We thank the original dataset providers for their contributions to the shape analysis community, and that all credits should go to the original authors.

Data precomputation

python preprocess_dataset.py  

Train

To train the model on a specified dataset.

python train.py --opt options/train/faust.yaml 

You can visualize the training process in tensorboard.

tensorboard --logdir experiments/

Test

To test the model on a specified dataset.

python test.py --opt options/test/faust.yaml 

The qualitative and quantitative results will be saved in results folder.

Texture Transfer

An example of texture transfer is provided in texture_transfer.py

python texture_transfer.py

Pretrained models

You can find all pre-trained models in checkpoints for reproducibility.

Results

You can find all matching results in results.

Acknowledgement

The framework implementation is adapted from Unsupervised Learning of Robust Spectral Shape Matching.
The feature learning network implementation is adapted from DiffusionNet

Attribution

Please cite our paper when using the code. You can use the following bibtex

@inproceedings{luo2026unsupervised,
  title={Unsupervised Contrastive Learning for Efficient and Robust Spectral Shape Matching},
  author={Luo, Feifan and Chen, Hongyang},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={40},
  number={9},
  pages={7662--7670},
  year={2026}
}