HDNET: Exploiting HD Maps for 3D Object Detection

12/21/2020
by   Bin Yang, et al.
0

In this paper we show that High-Definition (HD) maps provide strong priors that can boost the performance and robustness of modern 3D object detectors. Towards this goal, we design a single stage detector that extracts geometric and semantic features from the HD maps. As maps might not be available everywhere, we also propose a map prediction module that estimates the map on the fly from raw LiDAR data. We conduct extensive experiments on KITTI as well as a large-scale 3D detection benchmark containing 1 million frames, and show that the proposed map-aware detector consistently outperforms the state-of-the-art in both mapped and un-mapped scenarios. Importantly the whole framework runs at 20 frames per second.

READ FULL TEXT
03/10/2021

MapFusion: A General Framework for 3D Object Detection with HDMaps

3D object detection is a key perception component in autonomous driving....
09/03/2019

Map plasticity

With the arrival of digital maps, the ubiquity of maps has increased sha...
12/20/2020

Deep Continuous Fusion for Multi-Sensor 3D Object Detection

In this paper, we propose a novel 3D object detector that can exploit bo...
09/15/2021

FFAVOD: Feature Fusion Architecture for Video Object Detection

A significant amount of redundancy exists between consecutive frames of ...
09/06/2019

Geometry-Aware Video Object Detection for Static Cameras

In this paper we propose a geometry-aware model for video object detecti...
05/02/2022

Cost-Aware Evaluation and Model Scaling for LiDAR-Based 3D Object Detection

Considerable research efforts have been devoted to LiDAR-based 3D object...
09/14/2018

Leveraging Heteroscedastic Aleatoric Uncertainties for Robust Real-Time LiDAR 3D Object Detection

We present a robust real-time LiDAR 3D object detector that leverages he...

Code Repositories

Lidar_For_AD_references

A list of references on lidar point cloud processing for autonomous driving


view repo