Object Detection in 3D Point Clouds via Local Correlation-Aware Point Embedding

TL;DR

This paper introduces a local neighborhood embedding technique for 3D object detection in point clouds, enhancing feature computation by considering neighboring points, leading to improved detection performance over existing methods.

Contribution

The paper proposes a novel local correlation-aware embedding operation that incorporates neighborhood information into point features, improving upon the original F-PointNet approach.

Findings

Achieves better detection accuracy than F-PointNet baseline

Demonstrates the effectiveness of neighborhood-aware feature computation

Improves 3D object detection performance on benchmark datasets

Abstract

We present an improved approach for 3D object detection in point cloud data based on the Frustum PointNet (F-PointNet). Compared to the original F-PointNet, our newly proposed method considers the point neighborhood when computing point features. The newly introduced local neighborhood embedding operation mimics the convolutional operations in 2D neural networks. Thus features of each point are not only computed with the features of its own or of the whole point cloud but also computed especially with respect to the features of its neighbors. Experiments show that our proposed method achieves better performance than the F-Pointnet baseline on 3D object detection tasks.