# ConvPoint: Continuous Convolutions for Point Cloud Processing

## TL;DR

This paper introduces ConvPoint, a continuous convolution approach for point cloud processing that generalizes CNNs to unstructured data, enabling flexible neural network design and achieving competitive results in shape classification and segmentation.

## Contribution

It proposes a novel continuous convolution method for point clouds, allowing arbitrary sizes and easy neural network design, outperforming existing methods in key tasks.

## Key findings

- Achieves competitive results on shape classification.
- Effective in part and semantic segmentation.
- Flexible architecture adaptable to various tasks.

## Abstract

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.