# Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior

arXiv: https://arxiv.org/abs/2606.31814 · HTML: https://mlsanity.com/paper/2606.31814/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 51 of its 56 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 30 of 51)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021)
- [Pix2seq: A Language Modeling Framework for Object Detection](https://mlsanity.com/paper/2109.10852/) (2021)
- [VectorMapNet: End-to-end Vectorized HD Map Learning](https://mlsanity.com/paper/2206.08920/) (2022)
- [Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?](https://mlsanity.com/paper/2206.07959/) (2022)
- [Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images](https://mlsanity.com/paper/2110.01997/) (2021)
- [OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping](https://mlsanity.com/paper/2304.10440/) (2023)
- [Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation Maps](https://mlsanity.com/paper/2311.04079/) (2023)
- [Graph-based Topology Reasoning for Driving Scenes](https://mlsanity.com/paper/2304.05277/) (2023)
- [P-MapNet: Far-seeing Map Generator Enhanced by both SDMap and HDMap Priors](https://mlsanity.com/paper/2403.10521/) (2024)
- [Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction](https://mlsanity.com/paper/2303.08815/) (2023)
- [TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning](https://mlsanity.com/paper/2310.06753/) (2023)
- [Object as Query: Lifting any 2D Object Detector to 3D Detection](https://mlsanity.com/paper/2301.02364/) (2023)
- [T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving](https://mlsanity.com/paper/2411.18894/) (2024)
- [FlowTok: Flowing Seamlessly Across Text and Image Tokens](https://mlsanity.com/paper/2503.10772/) (2025)
- [TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes](https://mlsanity.com/paper/2405.14747/) (2024)
- [Complementing Onboard Sensors with Satellite Map: A New Perspective for HD Map Construction](https://mlsanity.com/paper/2308.15427/) (2023)
- [Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments](https://mlsanity.com/paper/2503.22496/) (2025)
- [SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic](https://mlsanity.com/paper/2403.17933/) (2024)
- [Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution](https://mlsanity.com/paper/2412.15213/) (2024)
- [MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models](https://mlsanity.com/paper/2308.12963/) (2023)
- [Enhancing 3D Lane Detection and Topology Reasoning with 2D Lane Priors](https://mlsanity.com/paper/2406.03105/) (2024)
- [Learning and Aggregating Lane Graphs for Urban Automated Driving](https://mlsanity.com/paper/2302.06175/) (2023)
- [Lane Graph Estimation for Scene Understanding in Urban Driving](https://mlsanity.com/paper/2105.00195/) (2021)

## Abstract (arXiv)

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.