# Enabling 3D Object Detection with a Low-Resolution LiDAR

arXiv: https://arxiv.org/abs/2105.01765 · HTML: https://mlsanity.com/paper/2105.01765/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 4 May 2021.

## Builds on (most cited first, 7 of 7)

- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera](https://mlsanity.com/paper/1807.00275/) (2018)
- [End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection](https://mlsanity.com/paper/2004.03080/) (2020)
- [A Comprehensive Study and Comparison of Core Technologies for MPEG 3D Point Cloud Compression](https://mlsanity.com/paper/1912.09674/) (2019)
- [BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye View](https://mlsanity.com/paper/2003.04188/) (2020)
- [Road Segmentation on low resolution Lidar point clouds for autonomous vehicles](https://mlsanity.com/paper/2005.13102/) (2020)

## Abstract (arXiv)

Light Detection And Ranging (LiDAR) has been widely used in autonomous vehicles for perception and localization. However, the cost of a high-resolution LiDAR is still prohibitively expensive, while its low-resolution counterpart is much more affordable. Therefore, using low-resolution LiDAR for autonomous driving is an economically viable solution, but the point cloud sparsity makes it extremely challenging. In this paper, we propose a two-stage neural network framework that enables 3D object detection using a low-resolution LiDAR. Taking input from a low-resolution LiDAR point cloud and a monocular camera image, a depth completion network is employed to produce dense point cloud that is subsequently processed by a voxel-based network for 3D object detection. Evaluated with KITTI dataset for 3D object detection in Bird-Eye View (BEV), the experimental result shows that the proposed approach performs significantly better than directly applying the 16-line LiDAR point cloud for object detection. For both easy and moderate cases, our 3D vehicle detection results are close to those using 64-line high-resolution LiDARs.