GeoReFormer: Geometry-Aware Refinement for Lane Segment Detection and Topology Reasoning

2026-03-26

AI Summary

This work addresses the limitations of existing query-based Transformer approaches in 3D lane detection and topology reasoning, which often lack explicit modeling of geometric continuity and graph-structured relationships, leading to suboptimal accuracy and topological consistency. To overcome this, the authors propose GeoReFormer, a unified query-driven architecture that embeds geometry- and topology-aware inductive biases directly into the Transformer decoder. Key innovations include data-driven geometric priors for structured query initialization, a bounded coordinate space refinement mechanism to ensure polyline deformation stability, and a per-query gated topology propagation module for selective integration of relational context. Evaluated on the OpenLane-V2 benchmark, GeoReFormer achieves a state-of-the-art mAP of 34.5%, substantially outperforming existing Transformer baselines while significantly improving topological consistency.

Abstract

Accurate 3D lane segment detection and topology reasoning are critical for structured online map construction in autonomous driving. Recent transformer-based approaches formulate this task as query-based set prediction, yet largely inherit decoder designs originally developed for compact object detection. However, lane segments are continuous polylines embedded in directed graphs, and generic query initialization and unconstrained refinement do not explicitly encode this geometric and relational structure. We propose GeoReFormer (Geometry-aware Refinement Transformer), a unified query-based architecture that embeds geometry- and topology-aware inductive biases directly within the transformer decoder. GeoReFormer introduces data-driven geometric priors for structured query initialization, bounded coordinate-space refinement for stable polyline deformation, and per-query gated topology propagation to selectively integrate relational context. On the OpenLane-V2 benchmark, GeoReFormer achieves state-of-the-art performance with 34.5% mAP while improving topology consistency over strong transformer baselines, demonstrating the utility of explicit geometric and relational structure encoding.

Problem

• lane segment detection
• topology reasoning
• geometry-aware
• transformer decoder
• structured map construction

Innovation

• Geometry-aware refinement
• Query-based lane detection
• Topology reasoning
• Structured query initialization
• Bounded coordinate-space deformation