Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point clouds

TL;DR

Voxel-FPN introduces a novel multi-scale voxel feature aggregation method for 3D object detection from point clouds, improving feature extraction and performance in autonomous driving scenarios.

Contribution

It presents a one-stage 3D object detector with a unique encoder-decoder architecture for multi-scale voxel feature fusion, outperforming existing baselines.

Findings

Better feature extraction from point cloud data.

Superior performance on KITTI-3D benchmark.

Effective balance of speed and accuracy.

Abstract

Object detection in point cloud data is one of the key components in computer vision systems, especially for autonomous driving applications. In this work, we present Voxel-FPN, a novel one-stage 3D object detector that utilizes raw data from LIDAR sensors only. The core framework consists of an encoder network and a corresponding decoder followed by a region proposal network. Encoder extracts multi-scale voxel information in a bottom-up manner while decoder fuses multiple feature maps from various scales in a top-down way. Extensive experiments show that the proposed method has better performance on extracting features from point data and demonstrates its superiority over some baselines on the challenging KITTI-3D benchmark, obtaining good performance on both speed and accuracy in real-world scenarios.