Online Vectorized HD Map Construction using Geometry
- URL: http://arxiv.org/abs/2312.03341v2
- Date: Wed, 10 Jul 2024 08:46:19 GMT
- Title: Online Vectorized HD Map Construction using Geometry
- Authors: Zhixin Zhang, Yiyuan Zhang, Xiaohan Ding, Fusheng Jin, Xiangyu Yue,
- Abstract summary: We propose GeMap, which learns Euclidean shapes and relations of map instances beyond basic perception.
Our method achieves new state-of-the-art performance on the NuScenes and Argoverse 2 datasets.
- Score: 17.33973935325903
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The construction of online vectorized High-Definition (HD) maps is critical for downstream prediction and planning. Recent efforts have built strong baselines for this task, however, shapes and relations of instances in urban road systems are still under-explored, such as parallelism, perpendicular, or rectangle-shape. In our work, we propose GeMap ($\textbf{Ge}$ometry $\textbf{Map}$), which end-to-end learns Euclidean shapes and relations of map instances beyond basic perception. Specifically, we design a geometric loss based on angle and distance clues, which is robust to rigid transformations. We also decouple self-attention to independently handle Euclidean shapes and relations. Our method achieves new state-of-the-art performance on the NuScenes and Argoverse 2 datasets. Remarkably, it reaches a 71.8% mAP on the large-scale Argoverse 2 dataset, outperforming MapTR V2 by +4.4% and surpassing the 70% mAP threshold for the first time. Code is available at https://github.com/cnzzx/GeMap.
Related papers
- ADMap: Anti-disturbance framework for reconstructing online vectorized
HD map [9.218463154577616]
This paper proposes the Anti-disturbance Map reconstruction framework (ADMap)
To mitigate point-order jitter, the framework consists of three modules: Multi-Scale Perception Neck, Instance Interactive Attention (IIA), and Vector Direction Difference Loss (VDDL)
arXiv Detail & Related papers (2024-01-24T01:37:27Z) - ScalableMap: Scalable Map Learning for Online Long-Range Vectorized HD
Map Construction [42.874195888422584]
We propose a novel end-to-end pipeline for online long-range vectorized high-definition (HD) map construction using on-board camera sensors.
We exploit the properties of map elements to improve the performance of map construction.
arXiv Detail & Related papers (2023-10-20T09:46:24Z) - Online Map Vectorization for Autonomous Driving: A Rasterization
Perspective [58.71769343511168]
We introduce a newization-based evaluation metric, which has superior sensitivity and is better suited to real-world autonomous driving scenarios.
We also propose MapVR (Map Vectorization via Rasterization), a novel framework that applies differentiableization to preciseized outputs and then performs geometry-aware supervision on HD maps.
arXiv Detail & Related papers (2023-06-18T08:51:14Z) - 3D Line Mapping Revisited [86.13455066577657]
LIMAP is a library for 3D line mapping that robustly and efficiently creates 3D line maps from multi-view imagery.
Our code integrates seamlessly with existing point-based Structure-from-Motion methods.
Our robust 3D line maps also open up new research directions.
arXiv Detail & Related papers (2023-03-30T16:14:48Z) - VectorMapNet: End-to-end Vectorized HD Map Learning [18.451587680552464]
We introduce an end-to-end vectorized HD map learning pipeline, termed VectorMapNet.
This pipeline can explicitly model the spatial relation between map elements and generate vectorized maps friendly to downstream autonomous driving tasks.
Experiments show that VectorMapNet achieve strong map learning performance on both nuScenes and Argo2 dataset.
arXiv Detail & Related papers (2022-06-17T17:57:13Z) - HDMapNet: An Online HD Map Construction and Evaluation Framework [23.19001503634617]
HD map construction is a crucial problem for autonomous driving.
Traditional HD maps are coupled with centimeter-level accurate localization which is unreliable in many scenarios.
Online map learning is a more scalable way to provide semantic and geometry priors to self-driving vehicles.
arXiv Detail & Related papers (2021-07-13T18:06:46Z) - HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps [81.86923212296863]
HD maps are maps with precise definitions of road lanes with rich semantics of the traffic rules.
There are only a small amount of real-world road topologies and geometries, which significantly limits our ability to test out the self-driving stack.
We propose HDMapGen, a hierarchical graph generation model capable of producing high-quality and diverse HD maps.
arXiv Detail & Related papers (2021-06-28T17:59:30Z) - DAGMapper: Learning to Map by Discovering Lane Topology [84.12949740822117]
We focus on drawing the lane boundaries of complex highways with many lanes that contain topology changes due to forks and merges.
We formulate the problem as inference in a directed acyclic graphical model (DAG), where the nodes of the graph encode geometric and topological properties of the local regions of the lane boundaries.
We show the effectiveness of our approach on two major North American Highways in two different states and show high precision and recall as well as 89% correct topology.
arXiv Detail & Related papers (2020-12-22T21:58:57Z) - Hierarchical Recurrent Attention Networks for Structured Online Maps [91.28820076955128]
We tackle the problem of online road network extraction from sparse 3D point clouds.
Our method is inspired by how annotator builds a lane graph, by first identifying how many lanes there are and then drawing each one in turn.
We develop a hierarchical recurrent network that attends to initial regions of a lane boundary and traces them out completely by outputting a structured polyline.
arXiv Detail & Related papers (2020-12-22T19:35:53Z) - Label Decoupling Framework for Salient Object Detection [157.96262922808245]
Recent methods mainly focus on aggregating multi-level features from convolutional network (FCN) and introducing edge information as auxiliary supervision.
We propose a label decoupling framework (LDF) which consists of a label decoupling procedure and a feature interaction network (FIN)
Experiments on six benchmark datasets demonstrate that LDF outperforms state-of-the-art approaches on different evaluation metrics.
arXiv Detail & Related papers (2020-08-25T14:23:38Z) - SMAPGAN: Generative Adversarial Network Based Semi-Supervised Styled Map
Tiles Generating Method [0.0]
Traditional online map tiles, widely used on the Internet such as Google Map and Baidu Map, are rendered from vector data.
We propose a semi-supervised Generation of styled map Tiles based on Generative Adversarial Network (SMAPGAN) model.
Experimental results present that SMAPGAN outperforms state-of-the-art (SOTA) works according to mean squared error, structural similarity index, and ESSI.
arXiv Detail & Related papers (2020-01-21T04:13:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.