Journal Article10.48550/arXiv.2306.10502
Online Map Vectorization for Autonomous Driving: A Rasterization Perspective
16
TL;DR: In this article , the authors propose MapVR (Map Vectorization via Rasterization), a framework that applies differentiable rasterization to vectorized outputs and then performs precise and geometry-aware supervision on rasterized HD maps.
read more
Abstract: Vectorized high-definition (HD) map is essential for autonomous driving, providing detailed and precise environmental information for advanced perception and planning. However, current map vectorization methods often exhibit deviations, and the existing evaluation metric for map vectorization lacks sufficient sensitivity to detect these deviations. To address these limitations, we propose integrating the philosophy of rasterization into map vectorization. Specifically, we introduce a new rasterization-based evaluation metric, which has superior sensitivity and is better suited to real-world autonomous driving scenarios. Furthermore, we propose MapVR (Map Vectorization via Rasterization), a novel framework that applies differentiable rasterization to vectorized outputs and then performs precise and geometry-aware supervision on rasterized HD maps. Notably, MapVR designs tailored rasterization strategies for various geometric shapes, enabling effective adaptation to a wide range of map elements. Experiments show that incorporating rasterization into map vectorization greatly enhances performance with no extra computational cost during inference, leading to more accurate map perception and ultimately promoting safer autonomous driving.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction
Bencheng Liao,Shaoyu Chen,Yunchi Zhang,Bo Jiang,Xiang Zhang,Wenyu Liu,Chang-Ti Huang,Xinggang Wang +7 more
TL;DR: A unified permutation-equivalent modeling approach is proposed, modeling map element as a point set with a group of equivalent permutations, which accurately describes the shape of map element and stabilizes the learning process.
Online Vectorized HD Map Construction using Geometry
Zhixin Zhang,Yiyuan Zhang,Xiaohan Ding,Fusheng Jin,Xiangyu Yue +4 more
TL;DR: This work proposes GeMap, which end-to-end learns Euclidean shapes and relations of map instances beyond basic perception and achieves new state-of-the-art performance on the NuScenes and Argoverse 2 datasets.
12
HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction
Yi Zhou,Hui Zhang,Jiaqian Yu,Yifan Yang,Sangil Jung,Seungsang Park,ByungIn Yoo +6 more
TL;DR: HIMap is a hybrid representation learning framework for end-to-end vectorized HD map construction that effectively learns and interacts with point-level and element-level information.
11
P-MapNet: Far-seeing Map Generator Enhanced by both SDMap and HDMap Priors
Zhou Jiang,Zhenxin Zhu,Pengfei Li,Huan-ang Gao,Tianyuan Yuan,Yongliang Shi,Hang Zhao,Hao Zhao +7 more
TL;DR: P-MapNet incorporates priors from both SDMap and HDMap to improve online map generation performance at far regions.
8
Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation Maps
Katie Z Luo,Xinshuo Weng,Yan Wang,Shuang Wu,Jie Li,Kilian Q. Weinberger,Yue Wang,Marco Pavone +7 more
TL;DR: A novel framework to integrate SD maps into online map prediction is proposed and a Transformer-based encoder, SD Map Encoder Representations from transFormers, is proposed to leverage priors in SD maps for the lane-topology prediction task.
8
References
•Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
117.9K
•Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
- 12 Jun 2017
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin,Michael Maire,Serge Belongie,James Hays,Pietro Perona,Deva Ramanan,Piotr Dollár,C. Lawrence Zitnick +7 more
- 06 Sep 2014
TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.
The Pascal Visual Object Classes (VOC) Challenge
TL;DR: The state-of-the-art in evaluated methods for both classification and detection are reviewed, whether the methods are statistically different, what they are learning from the images, and what the methods find easy or confuse.
Focal Loss for Dense Object Detection
Tsung-Yi Lin,Priya Goyal,Ross Girshick,Kaiming He,Piotr Dollár +4 more
- 07 Aug 2017
TL;DR: This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.