# Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds

## TL;DR

This paper introduces Dilated Point Convolutions (DPC), which significantly increase the receptive field size in 3D point cloud processing, leading to improved performance in tasks like segmentation and classification.

## Contribution

The paper proposes a novel dilation mechanism for point convolutions that can be integrated into existing networks to enhance receptive field size.

## Key findings

- Receptive field size correlates with task performance.
- DPC significantly enlarges receptive fields in point convolutional networks.
- Networks with DPC achieve competitive benchmark scores.

## Abstract

In this work, we propose Dilated Point Convolutions (DPC). In a thorough ablation study, we show that the receptive field size is directly related to the performance of 3D point cloud processing tasks, including semantic segmentation and object classification. Point convolutions are widely used to efficiently process 3D data representations such as point clouds or graphs. However, we observe that the receptive field size of recent point convolutional networks is inherently limited. Our dilated point convolutions alleviate this issue, they significantly increase the receptive field size of point convolutions. Importantly, our dilation mechanism can easily be integrated into most existing point convolutional networks. To evaluate the resulting network architectures, we visualize the receptive field and report competitive scores on popular point cloud benchmarks.