UniMapGen: A Generative Framework for Large-Scale Map Construction from Multi-modal Data
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918195434094592 |
|---|---|
| author | Yuan, Yujian Wu, Changjie Chang, Xinyuan Wang, Sijin Zhang, Hang Liang, Shiyi Zeng, Shuang Xu, Mu Guo, Ning |
| author_facet | Yuan, Yujian Wu, Changjie Chang, Xinyuan Wang, Sijin Zhang, Hang Liang, Shiyi Zeng, Shuang Xu, Mu Guo, Ning |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22262 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniMapGen: A Generative Framework for Large-Scale Map Construction from Multi-modal Data Yuan, Yujian Wu, Changjie Chang, Xinyuan Wang, Sijin Zhang, Hang Liang, Shiyi Zeng, Shuang Xu, Mu Guo, Ning Computer Vision and Pattern Recognition 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. |
| title | UniMapGen: A Generative Framework for Large-Scale Map Construction from Multi-modal Data |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.22262 |