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

arXiv: https://arxiv.org/abs/1907.05286 · HTML: https://mlsanity.com/paper/1907.05286/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2019.

## Built on by (most cited first, 9 of 9)

- [PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection](https://mlsanity.com/paper/2102.00463/) (2021)
- [LiDAR R-CNN: An Efficient and Universal 3D Object Detector](https://mlsanity.com/paper/2103.15297/) (2021)
- [3D Object Detection for Autonomous Driving: A Survey](https://mlsanity.com/paper/2106.10823/) (2021)
- [PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection](https://mlsanity.com/paper/2205.07403/) (2022)
- [DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation](https://mlsanity.com/paper/2108.04023/) (2021)
- [Radars for Autonomous Driving: A Review of Deep Learning Methods and Challenges](https://mlsanity.com/paper/2306.09304/) (2023)
- [OCM3D: Object-Centric Monocular 3D Object Detection](https://mlsanity.com/paper/2104.06041/) (2021)
- [ImpDet: Exploring Implicit Fields for 3D Object Detection](https://mlsanity.com/paper/2203.17240/) (2022)
- [3D-FCT: Simultaneous 3D Object Detection and Tracking Using Feature Correlation](https://mlsanity.com/paper/2110.02531/) (2021)

## Abstract (arXiv)

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.