{"ID":2865295,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.22262","arxiv_id":"2509.22262","title":"UniMapGen: A Generative Framework for Large-Scale Map Construction from Multi-modal Data","abstract":"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 \\textbf{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 \\textbf{multi-modal} inputs, enabling dynamic selection among BEV, PV, and text prompt, to overcome the drawbacks of satellite data. (3) developing a \\textbf{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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2509.22262","url_pdf":"https://arxiv.org/pdf/2509.22262v2","authors":"[\"Yujian Yuan\",\"Changjie Wu\",\"Xinyuan Chang\",\"Sijin Wang\",\"Hang Zhang\",\"Shiyi Liang\",\"Shuang Zeng\",\"Mu Xu\",\"Ning Guo\"]","published":"2025-09-26T12:26:33Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}