ConvPoint: Continuous Convolutions for Point Cloud Processing
This work addresses the challenge of applying machine learning to point clouds, which are common in domains like robotics and 3D vision, by proposing a novel continuous convolution method.
The authors tackled the problem of processing unstructured point clouds by generalizing discrete CNNs to use continuous kernels, enabling flexible network design and handling arbitrary point cloud sizes. They achieved competitive results on shape classification, part segmentation, and semantic segmentation tasks compared to state-of-the-art methods.
Point clouds are unstructured and unordered data, as opposed to images. Thus, most machine learning approach developed for image cannot be directly transferred to point clouds. In this paper, we propose a generalization of discrete convolutional neural networks (CNNs) in order to deal with point clouds by replacing discrete kernels by continuous ones. This formulation is simple, allows arbitrary point cloud sizes and can easily be used for designing neural networks similarly to 2D CNNs. We present experimental results with various architectures, highlighting the flexibility of the proposed approach. We obtain competitive results compared to the state-of-the-art on shape classification, part segmentation and semantic segmentation for large-scale point clouds.