百科.dev
全部条目在线工具AI 编程趋势榜开源项目技术资讯提交条目
登录
< 返回工具列表
P

P-MapNet

> 编程语言
开源

由 RAL 接收

198 stars0 点赞2 次浏览
访问官网GitHub

工具介绍

由 RAL 接收

P-MapNet: Far-seeing Map Generator Enhanced by both SDMap and HDMap Priors

[RAL] [Paper] [Project Page]

Abstract: Autonomous vehicles are gradually entering city roads today, with the help of high-definition maps (HDMaps). However, the reliance on HDMaps prevents autonomous vehicles from stepping into regions without this expensive digital infrastructure. This fact drives many researchers to study online HDMap construction algorithms, but the performance of these algorithms at far regions is still unsatisfying. We present P-MapNet, in which the letter P highlights the fact that we focus on incorporating map priors to improve model performance. Specifically, we exploit priors in both SDMap and HDMap. On one hand, we extract weakly aligned SDMap from OpenStreetMap, and encode it as an additional conditioning branch. Despite the misalignment challenge, our attention-based architecture adaptively attends to relevant SDMap skeletons and significantly improves performance. On the other hand, we exploit a masked autoencoder to capture the prior distribution of HDMap, which can serve as a refinement module to mitigate occlusions and artifacts. We benchmark on the nuScenes and Argoverse2 datasets. Through comprehensive experiments, we show that: (1) our SDMap prior can improve online map construction performance, using both rasterized (by up to +18.73 mIoU) and vectorized (by up to +8.50 mAP) output representations. (2) our HDMap prior can improve map perceptual metrics by up to 6.34%. (3) P-MapNet can be switched into different inference modes that covers different regions of the accuracy-efficiency trade-off landscape. (4) P-MapNet is a far-seeing solution that brings larger improvements on longer ranges.

Model

Results on nuScenes-val set

We provide results on nuScenes-val set.

Range Method M Div. Ped. Bound. mIoU Model Config
60 × 30 HDMapNet L+C 45.9 30.5 56.8 44.40 ckpt cfg
60 × 30 P-MapNet(SD+HD Prio.) L+C 54.2 41.3 63.7 53.07 ckpt cfg
120 × 60 HDMapNet L+C 53.6 37.8 57.1 49.50 ckpt cfg
120 × 60 P-MapNet(SD+HD Prio.) L+C 65.3 52.0 68.0 61.77 ckpt cfg
240 × 60 HDMapNet L+C 40.0 26.8 42.6 36.47 ckpt cfg
240 × 60 P-MapNet(SD+HD Prio.) L+C 53.0 42.6 54.2 49.93 ckpt cfg

The model weights under other settings can be downloaded at GoogleDrive or 百度云.

Getting Started

  • Installation
  • Train and Eval
  • visualization

TODO

  • Add Argoverse2 dataset model

Citation

If you found this paper or codebase useful, please cite our paper:

…

Issues· 0 开放

查看全部 Issues在 GitHub 打开

暂无开放 Issues,或尚未同步最近议题。

> 标签

Python

暂无评论,来聊聊你的看法吧

> 工具信息

发布日期2026年8月1日
最后更新2026年9月18日
分类编程语言
定价开源

> 相关工具

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言