From Feature Learning to Spectral Basis Learning: A Unifying and Flexible Framework for Efficient and Robust Shape Matching [CVPR 2026]

Installation

conda create -n basis_learning python=3.8 # create new viertual environment
conda activate basis_learning
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

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 matching_results_cvpr26.

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{luo2026feature,
  title={From Feature Learning to Spectral Basis Learning: A Unifying and Flexible Framework for Efficient and Robust Shape Matching},
  author={Luo, Feifan and Chen, Hongyang},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={31377--31388},
  year={2026}
}

Contact

If you have any questions, please feel free to contact me via email without any hesitation.