AI RESEARCH
OptiMVMap: Offline Vectorized Map Construction via Optimal Multi-vehicle Perspectives
arXiv CS.CV
•
ArXi:2604.17135v1 Announce Type: new Offline vectorized maps constitute critical infrastructure for high-precision autonomous driving and mapping services. Existing approaches rely predominantly on single ego-vehicle trajectories, which fundamentally suffer from viewpoint insufficiency: while memory-based methods extend observation time by aggregating ego-trajectory frames, they lack the spatial diversity needed to reveal occluded regions.