PointManifoldCut: Point-wise Augmentation in the Manifold for Point Clouds
Tianfang Zhu, Yue Guan, Anan Li

TL;DR
PointManifoldCut introduces a novel point cloud augmentation method that replaces embedded points within neural networks, improving classification, segmentation performance, and robustness against attacks and transformations.
Contribution
This paper proposes PointManifoldCut, a new augmentation technique that replaces neural network embedded points rather than raw coordinates, enhancing point cloud task performance.
Findings
Improves point cloud classification accuracy.
Enhances segmentation network performance.
Increases robustness to attacks and geometric transformations.
Abstract
Mixed-based point cloud augmentation is a popular solution to the problem of limited availability of large-scale public datasets. But the mismatch between mixed points and corresponding semantic labels hinders the further application in point-wise tasks such as part segmentation. This paper proposes a point cloud augmentation approach, PointManifoldCut(PMC), which replaces the neural network embedded points, rather than the Euclidean space coordinates. This approach takes the advantage that points at the higher levels of the neural network are already trained to embed its neighbors relations and mixing these representation will not mingle the relation between itself and its label. We set up a spatial transform module after PointManifoldCut operation to align the new instances in the embedded space. The effects of different hidden layers and methods of replacing points are also discussed…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
Topics3D Shape Modeling and Analysis · 3D Surveying and Cultural Heritage · Computer Graphics and Visualization Techniques
