PointManifoldCut: Point-wise Augmentation in the Manifold for Point Clouds
This addresses the issue of limited data availability for point cloud tasks like part segmentation, offering an incremental improvement over existing augmentation methods.
The paper tackles the problem of label mismatch in mixed-based point cloud augmentation for point-wise tasks by proposing PointManifoldCut, which replaces points in the neural network's embedded space rather than Euclidean coordinates, resulting in enhanced performance for classification and segmentation networks with added robustness to attacks and transformations.
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 in this paper. The experiments show that our proposed approach can enhance the performance of point cloud classification as well as segmentation networks, and brings them additional robustness to attacks and geometric transformations. The code of this paper is available at: https://github.com/fun0515/PointManifoldCut.