Log In Sign Up

Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN

by   Shiyi Lan, et al.

Recent advances in deep convolutional neural networks (CNNs) have motivated researchers to adapt CNNs to directly model points in 3D point clouds. Modeling local structure has been proven to be important for the success of convolutional architectures, and researchers exploited the modeling of local point sets in the feature extraction hierarchy. However, limited attention has been paid to explicitly model the geometric structure amongst points in a local region. To address this problem, we propose Geo-CNN, which applies a generic convolution-like operation dubbed as GeoConv to each point and its local neighborhood. Local geometric relationships among points are captured when extracting edge features between the center and its neighboring points. We first decompose the edge feature extraction process onto three orthogonal bases, and then aggregate the extracted features based on the angles between the edge vector and the bases. This encourages the network to preserve the geometric structure in Euclidean space throughout the feature extraction hierarchy. GeoConv is a generic and efficient operation that can be easily integrated into 3D point cloud analysis pipelines for multiple applications. We evaluate Geo-CNN on ModelNet40 and KITTI and achieve state-of-the-art performance.


Shrinking unit: a Graph Convolution-Based Unit for CNN-like 3D Point Cloud Feature Extractors

3D point clouds have attracted increasing attention in architecture, eng...

Local Model Feature Transformations

Local learning methods are a popular class of machine learning algorithm...

Local Grid Rendering Networks for 3D Object Detection in Point Clouds

The performance of 3D object detection models over point clouds highly d...

Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds

Boundary information plays a significant role in 2D image segmentation, ...

Point Clouds Learning with Attention-based Graph Convolution Networks

Point clouds data, as one kind of representation of 3D objects, are the ...

Pillar in Pillar: Multi-Scale and Dynamic Feature Extraction for 3D Object Detection in Point Clouds

Sparsity and varied density are two of the main obstacles for 3D detecti...

Learning Local Displacements for Point Cloud Completion

We propose a novel approach aimed at object and semantic scene completio...

Code Repositories


A Pytorch Implementation of “Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN”

view repo