TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Driving

TL;DR

TopoPoint is a novel framework that improves topology reasoning in autonomous driving by explicitly detecting lane endpoints and jointly reasoning over endpoints and lanes, leading to more accurate intersection understanding.

Contribution

It introduces a new method combining endpoint detection with topology reasoning, including Point-Lane Merge Self-Attention and Point-Lane Graph Convolutional Network, to enhance robustness and accuracy.

Findings

Achieves state-of-the-art topology reasoning performance on OpenLane-V2.

Outperforms existing endpoint detection methods significantly.

Demonstrates robustness in lane endpoint refinement during inference.

Abstract

Topology reasoning, which unifies perception and structured reasoning, plays a vital role in understanding intersections for autonomous driving. However, its performance heavily relies on the accuracy of lane detection, particularly at connected lane endpoints. Existing methods often suffer from lane endpoints deviation, leading to incorrect topology construction. To address this issue, we propose TopoPoint, a novel framework that explicitly detects lane endpoints and jointly reasons over endpoints and lanes for robust topology reasoning. During training, we independently initialize point and lane query, and proposed Point-Lane Merge Self-Attention to enhance global context sharing through incorporating geometric distances between points and lanes as an attention mask . We further design Point-Lane Graph Convolutional Network to enable mutual feature aggregation between point and lane query. During inference, we introduce Point-Lane Geometry Matching algorithm that computes distances between detected points and lanes to refine lane endpoints, effectively mitigating endpoint deviation. Extensive experiments on the OpenLane-V2 benchmark demonstrate that TopoPoint achieves state-of-the-art performance in topology reasoning (48.8 on OLS). Additionally, we propose DET$_p$ to evaluate endpoint detection, under which our method significantly outperforms existing approaches (52.6 v.s. 45.2 on DET$_p$). The code is released at https://github.com/Franpin/TopoPoint.