Grid-GCN for Fast and Scalable Point Cloud Learning

12/06/2019
by   Qiangeng Xu, et al.
0

Due to the sparsity and irregularity of the point cloud data, methods that directly consume points have become popular. Among all point-based models, graph convolutional networks (GCN) lead to notable performance by fully preserving the data granularity and exploiting point interrelation. However, point-based networks spend a significant amount of time on data structuring (e.g., Farthest Point Sampling (FPS) and neighbor points querying), which limit the speed and scalability. In this paper, we present a method, named Grid-GCN, for fast and scalable point cloud learning. Grid-GCN uses a novel data structuring strategy, Coverage-Aware Grid Query (CAGQ). By leveraging the efficiency of grid space, CAGQ improves spatial coverage while reducing the theoretical time complexity. Compared with popular sampling methods such as Farthest Point Sampling (FPS) and Ball Query, CAGQ achieves up to 50X speed-up. With a Grid Context Aggregation (GCA) module, Grid-GCN achieves state-of-the-art performance on major point cloud classification and segmentation benchmarks with significantly faster runtime than previous studies. Remarkably, Grid-GCN achieves the inference speed of 50fps on ScanNet using 81920 points per scene as input. The code will be released.

READ FULL TEXT
research
06/01/2021

VA-GCN: A Vector Attention Graph Convolution Network for learning on Point Clouds

Owing to the development of research on local aggregation operators, dra...
research
03/31/2023

IC-FPS: Instance-Centroid Faster Point Sampling Module for 3D Point-base Object Detection

3D object detection is one of the most important tasks in autonomous dri...
research
05/30/2022

PSNet: Fast Data Structuring for Hierarchical Deep Learning on Point Cloud

In order to retain more feature information of local areas on a point cl...
research
08/18/2022

An Adjustable Farthest Point Sampling Method for Approximately-sorted Point Cloud Data

Sampling is an essential part of raw point cloud data processing such as...
research
11/22/2017

3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks

The point cloud is gaining prominence as a method for representing 3D sh...
research
03/23/2020

Distilling Knowledge from Graph Convolutional Networks

Existing knowledge distillation methods focus on convolutional neural ne...
research
05/08/2023

CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation

Simulating showers of particles in highly-granular detectors is a key fr...

Please sign up or login with your details

Forgot password? Click here to reset