ScalableMap: Scalable Map Learning for Online Long-Range Vectorized HD
Map Construction
- URL: http://arxiv.org/abs/2310.13378v2
- Date: Mon, 8 Jan 2024 03:26:40 GMT
- Title: ScalableMap: Scalable Map Learning for Online Long-Range Vectorized HD
Map Construction
- Authors: Jingyi Yu and Zizhao Zhang and Shengfu Xia and Jizhang Sang
- Abstract summary: 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.
- Score: 42.874195888422584
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose a novel end-to-end pipeline for online long-range vectorized
high-definition (HD) map construction using on-board camera sensors. The
vectorized representation of HD maps, employing polylines and polygons to
represent map elements, is widely used by downstream tasks. However, previous
schemes designed with reference to dynamic object detection overlook the
structural constraints within linear map elements, resulting in performance
degradation in long-range scenarios. In this paper, we exploit the properties
of map elements to improve the performance of map construction. We extract more
accurate bird's eye view (BEV) features guided by their linear structure, and
then propose a hierarchical sparse map representation to further leverage the
scalability of vectorized map elements and design a progressive decoding
mechanism and a supervision strategy based on this representation. Our
approach, ScalableMap, demonstrates superior performance on the nuScenes
dataset, especially in long-range scenarios, surpassing previous
state-of-the-art model by 6.5 mAP while achieving 18.3 FPS. Code is available
at https://github.com/jingy1yu/ScalableMap.
Related papers
- TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior [70.84644266024571]
We propose to train a perception model to "see" standard definition maps (SDMaps)
We encode SDMap elements into neural spatial map representations and instance tokens, and then incorporate such complementary features as prior information.
Based on the lane segment representation framework, the model simultaneously predicts lanes, centrelines and their topology.
arXiv Detail & Related papers (2024-11-22T06:13:42Z) - Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation [14.480713752871521]
MapUnveiler is a novel paradigm of clip-level vectorized HD map construction.
It unveils the occluded map elements within a clip input by relating dense image representations with efficient clip tokens.
MapUnveiler associates inter-clip information through clip token propagation, effectively utilizing long-term temporal map information.
arXiv Detail & Related papers (2024-11-17T08:38:18Z) - Enhancing Vectorized Map Perception with Historical Rasterized Maps [37.48510990922406]
We propose HRMapNet, leveraging a low-cost Historical Rasterized Map to enhance online vectorized map perception.
The historicalized map can be easily constructed from past predicted vectorized results and provides valuable complementary information.
HRMapNet can be integrated with most online vectorized map perception methods.
arXiv Detail & Related papers (2024-09-01T05:22:33Z) - 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) - MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction [40.07726377230152]
High-definition (HD) map provides abundant and precise static environmental information of the driving scene.
We present textbfMap textbfTRansformer, an end-to-end framework for online vectorized HD map construction.
arXiv Detail & Related papers (2023-08-10T17:56:53Z) - 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) - 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) - 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) - HDNET: Exploiting HD Maps for 3D Object Detection [99.49035895393934]
We show that High-Definition (HD) maps provide strong priors that can boost the performance and robustness of modern 3D object detectors.
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.
arXiv Detail & Related papers (2020-12-21T21:59:54Z) - Learning Lane Graph Representations for Motion Forecasting [92.88572392790623]
We construct a lane graph from raw map data to preserve the map structure.
We exploit a fusion network consisting of four types of interactions, actor-to-lane, lane-to-lane, lane-to-actor and actor-to-actor.
Our approach significantly outperforms the state-of-the-art on the large scale Argoverse motion forecasting benchmark.
arXiv Detail & Related papers (2020-07-27T17:59:49Z)
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.