TopoStreamer: Temporal Lane Segment Topology Reasoning in Autonomous Driving

This enables end-to-end autonomous driving systems to perform road-dependent maneuvers such as turning and lane changing. However, the limitations in consistent positional embedding and temporal multiple attribute learning in existing methods hinder accurate road network reconstruction. To address these issues, we propose TopoStreamer, an end-to-end temporal perception model for lane segment topology reasoning. Specifically, TopoStreamer introduces three key improvements: streaming attribute constraints, dynamic lane boundary positional encoding, and lane segment denoising. The streaming attribute constraints enforce temporal consistency in both centerline and boundary coordinates, along with their classifications. Meanwhile, dynamic lane boundary positional encoding enhances the learning of up-to-date positional information within queries, while lane segment denoising helps capture diverse lane segment patterns, ultimately improving model performance. Additionally, we assess the accuracy of existing models using a lane boundary classification metric, which serves as a crucial measure for lane-changing scenarios in autonomous driving. On the OpenLane-V2 dataset, TopoStreamer demonstrates considerable improvements over state-of-the-art methods, achieving substantial performance gains of +3.0% mAP in lane segment perception and +1.7% OLS in centerline perception tasks. Code is accessible at https://github.com/YimingY Perception serves as a crucial component in end-to-end autonomous driving (Li et al., 2024b; Y ang et al., 2025b), providing essential road priors for planning.