CVAIDec 6, 2023

Online Vectorized HD Map Construction using Geometry

arXiv:2312.03341v254 citationsh-index: 12Has CodeECCV
AI Analysis

This work addresses the need for accurate HD maps for autonomous driving prediction and planning, representing an incremental improvement over existing baselines.

The paper tackles the problem of constructing online vectorized HD maps by improving the modeling of geometric shapes and relations like parallelism and perpendicularity, achieving a state-of-the-art 71.8% mAP on Argoverse 2, surpassing previous methods by +4.4%.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes