Pytorch implementation for ToThePoint results in the paper ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via Recycling by Xinglin Li, Jiajing Chen, Jinhui Ouyang, Hanhui Deng, Senem Velipasalar, Di Wu in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
python 3.8
Pytorch 1.7.1
In addition, please add the project folder to PYTHONPATH and pip install the following packages:
*********
- 3D object classification
- Few-shot 3D object classification
- 3D object part segmentation:
- ablation study:
If you find ToThePoint useful in your research, please consider citing: BibTex:
@InProceedings{Li_2023_CVPR,
author = {Li, Xinglin and Chen, Jiajing and Ouyang, Jinhui and Deng, Hanhui and Velipasalar, Senem and Wu, Di},
title = {ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via Recycling},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2023},
pages = {21781-21790}
}
or
Xinglin Li, Jiajing Chen, Jinhui Ouyang, Hanhui Deng, Senem Velipasalar, Di Wu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 21781-21790.
Reference