# Separated RoadTopoFormer

Source: [Separated RoadTopoFormer](<https://www.sota2.com/research/paper/68fa70001e209131cea487a3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:52:23.574Z

Authors: Mingjie Lu, Yuanxian Huang, Ji Liu, Jinzhang Peng, Lu Tian, Ashish Sirasao

Published: 2023-07-04T08:21:39.000Z

## Abstract

Understanding driving scenarios is crucial to realizing autonomous driving. Previous works such as map learning and BEV lane detection neglect the connection relationship between lane instances, and traffic elements detection tasks usually neglect the relationship with lane lines. To address these issues, the task is presented which includes 4 sub-tasks, the detection of traffic elements, the detection of lane centerlines, reasoning connection relationships among lanes, and reasoning assignment relationships between lanes and traffic elements. We present Separated RoadTopoFormer to tackle the issues, which is an end-to-end framework that detects lane centerline and traffic elements with reasoning relationships among them. We optimize each module separately to prevent interaction with each other and aggregate them together with few finetunes. For two detection heads, we adopted a DETR-like architecture to detect objects, and for the relationship head, we concat two instance features from front detectors and feed them to the classifier to obtain relationship probability. Our final submission achieves 0.445 OLS, which is competitive in both sub-task and combined scores.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Scene Structure Perception on OpenLane-V2 (test)](<https://www.sota2.com/research/sota/scene-structure-perception-on-openlane-v2-test.md>): Scene Structure Perception; OpenLane-V2 (test); DET\_l: 22.

- [Lane Topology Extraction on OpenLane V2 (val)](<https://www.sota2.com/research/sota/lane-topology-extraction-on-openlane-v2-val.md>): Lane Topology Extraction; OpenLane V2 (val); DETl (Detection Error Left): 26.95.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2307.01557>)

[PDF](<https://arxiv.org/pdf/2307.01557.pdf>)
