# UniMapGen: A Generative Framework for Large-Scale Map Construction from Multi-modal Data

arXiv: https://arxiv.org/abs/2509.22262 · HTML: https://mlsanity.com/paper/2509.22262/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2208.14437/) (2022)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images](https://mlsanity.com/paper/1805.06561/) (2018)
- [VectorMapNet: End-to-end Vectorized HD Map Learning](https://mlsanity.com/paper/2206.08920/) (2022)
- [MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2308.05736/) (2023)
- [PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction](https://mlsanity.com/paper/2308.16477/) (2023)
- [MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping](https://mlsanity.com/paper/2403.15951/) (2024)
- [Graph-based Topology Reasoning for Driving Scenes](https://mlsanity.com/paper/2304.05277/) (2023)
- [Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction](https://mlsanity.com/paper/2303.08815/) (2023)
- [SMART: Advancing Scalable Map Priors for Driving Topology Reasoning](https://mlsanity.com/paper/2502.04329/) (2025)
- [OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction](https://mlsanity.com/paper/2410.23278/) (2024)

## Built on by (most cited first, 4 of 4)

- [MindDriver: Introducing Progressive Multimodal Reasoning for Autonomous Driving](https://mlsanity.com/paper/2602.21952/) (2026)
- [EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence](https://mlsanity.com/paper/2512.15160/) (2025)
- [AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction](https://mlsanity.com/paper/2512.19150/) (2025)
- [From Fragments to Global Maps: Learning Vectorized Map Aggregation with Large Language Models](https://mlsanity.com/paper/2610.02513/) (2026)

## Abstract (arXiv)

Large-scale map construction plays a vital role in applications like autonomous driving and navigation systems. Traditional large-scale map construction approaches mainly rely on costly and inefficient special data collection vehicles and labor-intensive annotation processes. While existing satellite-based methods have demonstrated promising potential in enhancing the efficiency and coverage of map construction, they exhibit two major limitations: (1) inherent drawbacks of satellite data (e.g., occlusions, outdatedness) and (2) inefficient vectorization from perception-based methods, resulting in discontinuous and rough roads that require extensive post-processing. This paper presents a novel generative framework, UniMapGen, for large-scale map construction, offering three key innovations: (1) representing lane lines as discrete sequence and establishing an iterative strategy to generate more complete and smooth map vectors than traditional perception-based methods. (2) proposing a flexible architecture that supports multi-modal inputs, enabling dynamic selection among BEV, PV, and text prompt, to overcome the drawbacks of satellite data. (3) developing a state update strategy for global continuity and consistency of the constructed large-scale map. UniMapGen achieves state-of-the-art performance on the OpenSatMap dataset. Furthermore, UniMapGen can infer occluded roads and predict roads missing from dataset annotations. Our code will be released.