KPConv: Flexible and Deformable Convolution for Point Clouds
This work addresses the challenge of efficiently processing point clouds for tasks like classification and segmentation, offering a novel convolution design that improves performance over existing methods.
The authors tackled the problem of point cloud processing by introducing KPConv, a flexible and deformable convolution method that operates directly on point clouds without intermediate representations, achieving state-of-the-art results in classification and segmentation on multiple datasets.
We present Kernel Point Convolution (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation. The convolution weights of KPConv are located in Euclidean space by kernel points, and applied to the input points close to them. Its capacity to use any number of kernel points gives KPConv more flexibility than fixed grid convolutions. Furthermore, these locations are continuous in space and can be learned by the network. Therefore, KPConv can be extended to deformable convolutions that learn to adapt kernel points to local geometry. Thanks to a regular subsampling strategy, KPConv is also efficient and robust to varying densities. Whether they use deformable KPConv for complex tasks, or rigid KPconv for simpler tasks, our networks outperform state-of-the-art classification and segmentation approaches on several datasets. We also offer ablation studies and visualizations to provide understanding of what has been learned by KPConv and to validate the descriptive power of deformable KPConv.