MapFusion: A Novel BEV Feature Fusion Network for Multi-modal Map Construction

TL;DR

The document presents a software bundle providing LaTeX class files cas-sc.cls and cas-dc.cls along with templates for formatting journal articles for Elsevier's updated workflow. It supports single- and double-column layouts and includes options such as longmktitle to manage extensive front matter. The guide covers author affiliation formatting, footnotes, and the placement of abstract, keywords, and main content within a structured front matter. The package aims to simplify manuscript preparation and ensure compatibility with Elsevier submission systems. The included examples (tmp.tex) illustrate front-matter and main text organization.

Abstract

Map construction task plays a vital role in providing precise and comprehensive static environmental information essential for autonomous driving systems. Primary sensors include cameras and LiDAR, with configurations varying between camera-only, LiDAR-only, or camera-LiDAR fusion, based on cost-performance considerations. While fusion-based methods typically perform best, existing approaches often neglect modality interaction and rely on simple fusion strategies, which suffer from the problems of misalignment and information loss. To address these issues, we propose MapFusion, a novel multi-modal Bird's-Eye View (BEV) feature fusion method for map construction. Specifically, to solve the semantic misalignment problem between camera and LiDAR BEV features, we introduce the Cross-modal Interaction Transform (CIT) module, enabling interaction between two BEV feature spaces and enhancing feature representation through a self-attention mechanism. Additionally, we propose an effective Dual Dynamic Fusion (DDF) module to adaptively select valuable information from different modalities, which can take full advantage of the inherent information between different modalities. Moreover, MapFusion is designed to be simple and plug-and-play, easily integrated into existing pipelines. We evaluate MapFusion on two map construction tasks, including High-definition (HD) map and BEV map segmentation, to show its versatility and effectiveness. Compared with the state-of-the-art methods, MapFusion achieves 3.6% and 6.2% absolute improvements on the HD map construction and BEV map segmentation tasks on the nuScenes dataset, respectively, demonstrating the superiority of our approach.