Projection-based Point Convolution for Efficient Point Cloud Segmentation

TL;DR

This paper introduces Projection-based Point Convolution (PPConv), a novel method for point cloud segmentation that leverages 2D convolutions and MLPs to improve processing speed and efficiency over existing point-based and voxel-based methods.

Contribution

PPConv is a new point convolutional module that avoids traditional point or voxel-based convolutions, enabling faster and more efficient point cloud processing.

Findings

PPConv achieves superior efficiency in segmentation tasks.

It outperforms state-of-the-art methods in inference time.

Experimental results on S3DIS and ShapeNetPart validate its effectiveness.

Abstract

Understanding point cloud has recently gained huge interests following the development of 3D scanning devices and the accumulation of large-scale 3D data. Most point cloud processing algorithms can be classified as either point-based or voxel-based methods, both of which have severe limitations in processing time or memory, or both. To overcome these limitations, we propose Projection-based Point Convolution (PPConv), a point convolutional module that uses 2D convolutions and multi-layer perceptrons (MLPs) as its components. In PPConv, point features are processed through two branches: point branch and projection branch. Point branch consists of MLPs, while projection branch transforms point features into a 2D feature map and then apply 2D convolutions. As PPConv does not use point-based or voxel-based convolutions, it has advantages in fast point cloud processing. When combined with a learnable projection and effective feature fusion strategy, PPConv achieves superior efficiency compared to state-of-the-art methods, even with a simple architecture based on PointNet++. We demonstrate the efficiency of PPConv in terms of the trade-off between inference time and segmentation performance. The experimental results on S3DIS and ShapeNetPart show that PPConv is the most efficient method among the compared ones. The code is available at github.com/pahn04/PPConv.