Spatially and Spectrally Consistent Deep Functional Maps
[Mingze Sun]1, [Shiwei Mao]1, [Puhua Jiang]1,2, [Maks Ovsjanikov]3, [Ruqi Huang]1
1 Tsinghua Shenzhen International Graduate School, China, 2 Peng Cheng Laboratory, China,
3 LIX, Ecole polytechnique, IP Paris, France
ICCV, 2023
In this paper, we formulate a simple yet effective two-branch design of unsupervised DFM based on our theoretical justification, which introduces spatially cycle consistency.
Qualitative visualizations of segmentation results:
Dependencies can be installed using:
pip install -r requirements.txt
Within each dataset folder, the following structure is expected:
SCPAE_r/
├── shapes_train
└── shapes_test
└── corres
python train.py --config scape_r
python eval.py --config scape_r --model_path ckpt.pth --save_path results_path
If you find this repository useful, please consider citing our paper:
@inproceedings{sun2023spatially,
title={Spatially and Spectrally Consistent Deep Functional Maps},
author={Sun, Mingze and Mao, Shiwei and Jiang, Puhua and Ovsjanikov, Maks and Huang, Ruqi},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
pages={14497--14507},
year={2023}
}