Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation

Jian Bi, Qianliang Wu, Xiang Li, Shuo Chen, Jianjun Qian, Lei Luo, Jian Yang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:4268-4288, 2025.

Abstract

Data augmentation has been widely used in machine learning. Its main goal is to transform and expand the original data using various techniques, creating a more diverse and enriched training dataset. However, due to the disorder and irregularity of point clouds, existing methods struggle to enrich geometric diversity and maintain topological consistency, leading to imprecise point cloud understanding. In this paper, we propose SinPoint, a novel method designed to preserve the topological structure of the original point cloud through a homeomorphism. It utilizes the Sine function to generate smooth displacements. This simulates object deformations, thereby producing a rich diversity of samples. In addition, we propose a Markov chain Augmentation Process to further expand the data distribution by combining different basic transformations through a random process. Our extensive experiments demonstrate that our method consistently outperforms existing Mixup and Deformation methods on various benchmark point cloud datasets, improving performance for shape classification and part segmentation tasks. Specifically, when used with PointNet++ and DGCNN, our method achieves a state-of-the-art accuracy of 90.2 in shape classification with the real-world ScanObjectNN dataset. We release the code at https://github.com/CSBJian/SinPoint.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-bi25b, title = {Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation}, author = {Bi, Jian and Wu, Qianliang and Li, Xiang and Chen, Shuo and Qian, Jianjun and Luo, Lei and Yang, Jian}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {4268--4288}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/bi25b/bi25b.pdf}, url = {https://proceedings.mlr.press/v267/bi25b.html}, abstract = {Data augmentation has been widely used in machine learning. Its main goal is to transform and expand the original data using various techniques, creating a more diverse and enriched training dataset. However, due to the disorder and irregularity of point clouds, existing methods struggle to enrich geometric diversity and maintain topological consistency, leading to imprecise point cloud understanding. In this paper, we propose SinPoint, a novel method designed to preserve the topological structure of the original point cloud through a homeomorphism. It utilizes the Sine function to generate smooth displacements. This simulates object deformations, thereby producing a rich diversity of samples. In addition, we propose a Markov chain Augmentation Process to further expand the data distribution by combining different basic transformations through a random process. Our extensive experiments demonstrate that our method consistently outperforms existing Mixup and Deformation methods on various benchmark point cloud datasets, improving performance for shape classification and part segmentation tasks. Specifically, when used with PointNet++ and DGCNN, our method achieves a state-of-the-art accuracy of 90.2 in shape classification with the real-world ScanObjectNN dataset. We release the code at https://github.com/CSBJian/SinPoint.} }
Endnote
%0 Conference Paper %T Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation %A Jian Bi %A Qianliang Wu %A Xiang Li %A Shuo Chen %A Jianjun Qian %A Lei Luo %A Jian Yang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-bi25b %I PMLR %P 4268--4288 %U https://proceedings.mlr.press/v267/bi25b.html %V 267 %X Data augmentation has been widely used in machine learning. Its main goal is to transform and expand the original data using various techniques, creating a more diverse and enriched training dataset. However, due to the disorder and irregularity of point clouds, existing methods struggle to enrich geometric diversity and maintain topological consistency, leading to imprecise point cloud understanding. In this paper, we propose SinPoint, a novel method designed to preserve the topological structure of the original point cloud through a homeomorphism. It utilizes the Sine function to generate smooth displacements. This simulates object deformations, thereby producing a rich diversity of samples. In addition, we propose a Markov chain Augmentation Process to further expand the data distribution by combining different basic transformations through a random process. Our extensive experiments demonstrate that our method consistently outperforms existing Mixup and Deformation methods on various benchmark point cloud datasets, improving performance for shape classification and part segmentation tasks. Specifically, when used with PointNet++ and DGCNN, our method achieves a state-of-the-art accuracy of 90.2 in shape classification with the real-world ScanObjectNN dataset. We release the code at https://github.com/CSBJian/SinPoint.
APA
Bi, J., Wu, Q., Li, X., Chen, S., Qian, J., Luo, L. & Yang, J.. (2025). Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:4268-4288 Available from https://proceedings.mlr.press/v267/bi25b.html.

Related Material