SeqGrowGraph: Learning Lane Topology as a Chain of Graph Expansions
Mengwei Xie, Shuang Zeng, Xinyuan Chang, Xinran Liu, Zheng Pan, Mu Xu, Xing Wei
Abstract
Accurate lane topology is essential for autonomous driving, yet traditional methods struggle to model the complex, non-linear structures--such as loops and bidirectional lanes--prevalent in real-world road structure. We present SeqGrowGraph, a novel framework that learns lane topology as a chain of graph expansions, inspired by human map-drawing processes. Representing the lane graph as a directed graph G=(V,E), with intersections (V) and centerlines (E), SeqGrowGraph incrementally constructs this graph by introducing one vertex at a time. At each step, an adjacency matrix (A) expands from nn to (n+1)(n+1) to encode connectivity, while a geometric matrix (M) captures centerline shapes as quadratic Bezier curves. The graph is serialized into sequences, enabling a transformer model to autoregressively predict the chain of expansions, guided by a depth-first search ordering. Evaluated on nuScenes and Argoverse 2 datasets, SeqGrowGraph achieves state-of-the-art performance.
BibTeX
@InProceedings{Xie_2025_ICCV,
author = {Xie, Mengwei and Zeng, Shuang and Chang, Xinyuan and Liu, Xinran and Pan, Zheng and Xu, Mu and Wei, Xing},
title = {SeqGrowGraph: Learning Lane Topology as a Chain of Graph Expansions},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2025},
pages = {27166-27175}
}