Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior

• URL: http://arxiv.org/abs/2606.31814v1
• Date: Tue, 30 Jun 2026 15:27:54 GMT
• Title: Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior
• Abstract summary: TopoGPT is a generative framework that learns the geometry prior to typical lane graph structures.<n>We construct a large-scale map dataset comprising 3.3M scenes.<n>TopoGPT outperforms existing methods by an average of +6.4 on lane-level and +11.6 on point-level metrics.
• Score: 35.786221225043455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Lane topology reasoning aims to construct a lane graph from onboard sensor observations. Existing methods follow a detection and association paradigm that treats each lane instance independently, leading to geometric inconsistency at connected endpoints and incomplete graphs due to visual occlusions. To address these issues, we propose TopoGPT, a generative framework that learns the geometry prior from typical lane graph structures through autoregressive sequence modeling. Specifically, we construct a large-scale map dataset comprising 3.3M scenes. For each lane graph, a lane tokenizer serializes it into discrete tokens, while a scene context encoder converts it into a rasterized image and extracts global features as scene tokens. We pre-train an autoregressive lane sequence transformer via scene-conditioned next-token prediction, endowing the model with the geometry prior over lane graph structures. Building upon this prior, a perception adapter aligns BEV features from multi-view images with the pre-trained scene condition, transferring the learned geometry prior to sensor-based lane graph prediction. On the OpenLane-V2 benchmark, TopoGPT outperforms existing methods by an average of +6.4 on lane-level and +11.6 on point-level metrics, and produces geometrically consistent and structurally complete lane graphs.

Related papers

• MapDreamer: Aerial Imagery Conditioned Latent Diffusion for Lane-Level Map Generation [11.066720921275648]
  We present MapDreamer, a generative diffusion model that synthesizes lane-level vector maps with explicit topology directly from a single aerial image.<n>To align generated maps with the observed scene, we condition each denoising step on dense aerial features injected through cross-attention.<n>Experiments on UrbanLaneGraph derived from Argoverse 2 show improved geometric and topological fidelity over non-generative baselines.
  arXiv  Detail & Related papers  (2026-07-01T18:33:38Z)
• Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching [35.40374108008262]
  Scene Graph Generation (SGG) unifies object localization and visual relationship reasoning by predicting boxes and subject-predicate-object triples.<n>We propose FlowSG, which recasts SGG as continuous-time transport on a hybrid discrete-continuous state.<n>Experiments on VG and PSG under closed- and open-vocabulary protocols show consistent gains in predicate R/mR and graph-level metrics.
  arXiv  Detail & Related papers  (2026-04-18T01:48:43Z)
• LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extraction [0.0]
  LineGraph2Road is a framework that improves connectedness prediction by formulating it as binary classification over edges in a constructed global but sparse Euclidean graph.<n>We evaluate it on three benchmarks: City-scale, SpaceNet, and Global-scale, and show that it achieves state-of-the-art results on two key metrics, TOPO-F1 and APLS.
  arXiv  Detail & Related papers  (2026-02-26T18:02:44Z)
• Global-Aware Edge Prioritization for Pose Graph Initialization [58.77851776918465]
  A core component of Structure-from-Motion (SfM) where images act as nodes and edges encode relative poses.<n>Since geometric verification is expensive, SfM pipelines restrict the pose graph to a sparse set of candidate edges.<n>We address this limitation through the concept of edge prioritization, ranking candidate edges by their utility for SfM.<n>Our approach has three components: (1) a GNN trained with SfM-derived supervision to predict globally consistent edge reliability; (2) multi-minimal-spanning-tree-based pose graph construction guided by these ranks; and (3) connectivity-aware score modulation that reinforces weak regions
  arXiv  Detail & Related papers  (2026-02-25T14:44:53Z)
• Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation [62.87088388345378]
  We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology.<n>Method leverages off-the-shelf geometry predictors to predict partial geometries viewed from reference images.<n>Cross-modal attention distillation is proposed to ensure accurate alignment between generated images and geometry.
  arXiv  Detail & Related papers  (2025-06-13T16:19:00Z)
• TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior [70.84644266024571]
  We propose to train a perception model to "see" standard definition maps (SDMaps) We encode SDMap elements into neural spatial map representations and instance tokens, and then incorporate such complementary features as prior information. Based on the lane segment representation framework, the model simultaneously predicts lanes, centrelines and their topology.
  arXiv  Detail & Related papers  (2024-11-22T06:13:42Z)
• SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks [14.548198408544032]
  We treat 3D scene graph alignment as a partial graph-matching problem and propose to solve it with a graph neural network. We reuse the geometric features learned by a point cloud registration method and associate the clustered point-level geometric features with the node-level semantic feature. We propose a point-matching rescoring method, that uses the node-wise alignment of the 3D scene graph to reweight the matching candidates from a pre-trained point cloud registration method.
  arXiv  Detail & Related papers  (2024-03-28T15:01:58Z)
• LaneGraph2Seq: Lane Topology Extraction with Language Model via Vertex-Edge Encoding and Connectivity Enhancement [34.017743757153866]
  Intricate road structures are often depicted using lane graphs, which include centerline curves and connections forming a Directed Acyclic Graph (DAG) We introduce LaneGraph2Seq, a novel approach for lane graph extraction. Our method demonstrates superior performance compared to state-of-the-art techniques in lane graph extraction.
  arXiv  Detail & Related papers  (2024-01-31T05:44:01Z)
• Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation [153.92387500677023]
  We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations. The proposed graph Transformer encoder combines graph convolutions and self-attentions in a Transformer to model both local and global interactions. We also propose a novel self-guided pre-training method for graph representation learning.
  arXiv  Detail & Related papers  (2024-01-15T14:36:38Z)
• Online Lane Graph Extraction from Onboard Video [133.68032636906133]
  We use the video stream from an onboard camera for online extraction of the surrounding's lane graph. Using video, instead of a single image, as input poses both benefits and challenges in terms of combining the information from different timesteps. A single model of this proposed simple, yet effective, method can process any number of images, including one, to produce accurate lane graphs.
  arXiv  Detail & Related papers  (2023-04-03T12:36:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.