PointMixup: Augmentation for Point Clouds
This addresses the need for effective data augmentation in 3D vision tasks like point cloud classification, though it's an incremental adaptation of existing mixup techniques from images to point clouds.
The paper tackles the problem of data augmentation for point clouds by introducing PointMixup, an interpolation method that generates new examples through optimal assignment between point clouds, proving it finds the shortest path with assignment invariance and linearity. Experiments show it improves point cloud classification, especially with scarce data, and increases robustness to noise and geometric transformations.
This paper introduces data augmentation for point clouds by interpolation between examples. Data augmentation by interpolation has shown to be a simple and effective approach in the image domain. Such a mixup is however not directly transferable to point clouds, as we do not have a one-to-one correspondence between the points of two different objects. In this paper, we define data augmentation between point clouds as a shortest path linear interpolation. To that end, we introduce PointMixup, an interpolation method that generates new examples through an optimal assignment of the path function between two point clouds. We prove that our PointMixup finds the shortest path between two point clouds and that the interpolation is assignment invariant and linear. With the definition of interpolation, PointMixup allows to introduce strong interpolation-based regularizers such as mixup and manifold mixup to the point cloud domain. Experimentally, we show the potential of PointMixup for point cloud classification, especially when examples are scarce, as well as increased robustness to noise and geometric transformations to points. The code for PointMixup and the experimental details are publicly available.