SafeMap: Robust HD Map Construction from Incomplete Observations

Xiaoshuai Hao, Lingdong Kong, Rong Yin, Pengwei Wang, Jing Zhang, Yunfeng Diao, Shu Zhao
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:22091-22102, 2025.

Abstract

Robust high-definition (HD) map construction is vital for autonomous driving, yet existing methods often struggle with incomplete multi-view camera data. This paper presents SafeMap, a novel framework specifically designed to ensure accuracy even when certain camera views are missing. SafeMap integrates two key components: the Gaussian-based Perspective View Reconstruction (G-PVR) module and the Distillation-based Bird’s-Eye-View (BEV) Correction (D-BEVC) module. G-PVR leverages prior knowledge of view importance to dynamically prioritize the most informative regions based on the relationships among available camera views. Furthermore, D-BEVC utilizes panoramic BEV features to correct the BEV representations derived from incomplete observations. Together, these components facilitate comprehensive data reconstruction and robust HD map generation. SafeMap is easy to implement and integrates seamlessly into existing systems, offering a plug-and-play solution for enhanced robustness. Experimental results demonstrate that SafeMap significantly outperforms previous methods in both complete and incomplete scenarios, highlighting its superior performance and resilience.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-hao25b, title = {{S}afe{M}ap: Robust {HD} Map Construction from Incomplete Observations}, author = {Hao, Xiaoshuai and Kong, Lingdong and Yin, Rong and Wang, Pengwei and Zhang, Jing and Diao, Yunfeng and Zhao, Shu}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {22091--22102}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/hao25b/hao25b.pdf}, url = {https://proceedings.mlr.press/v267/hao25b.html}, abstract = {Robust high-definition (HD) map construction is vital for autonomous driving, yet existing methods often struggle with incomplete multi-view camera data. This paper presents SafeMap, a novel framework specifically designed to ensure accuracy even when certain camera views are missing. SafeMap integrates two key components: the Gaussian-based Perspective View Reconstruction (G-PVR) module and the Distillation-based Bird’s-Eye-View (BEV) Correction (D-BEVC) module. G-PVR leverages prior knowledge of view importance to dynamically prioritize the most informative regions based on the relationships among available camera views. Furthermore, D-BEVC utilizes panoramic BEV features to correct the BEV representations derived from incomplete observations. Together, these components facilitate comprehensive data reconstruction and robust HD map generation. SafeMap is easy to implement and integrates seamlessly into existing systems, offering a plug-and-play solution for enhanced robustness. Experimental results demonstrate that SafeMap significantly outperforms previous methods in both complete and incomplete scenarios, highlighting its superior performance and resilience.} }
Endnote
%0 Conference Paper %T SafeMap: Robust HD Map Construction from Incomplete Observations %A Xiaoshuai Hao %A Lingdong Kong %A Rong Yin %A Pengwei Wang %A Jing Zhang %A Yunfeng Diao %A Shu Zhao %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-hao25b %I PMLR %P 22091--22102 %U https://proceedings.mlr.press/v267/hao25b.html %V 267 %X Robust high-definition (HD) map construction is vital for autonomous driving, yet existing methods often struggle with incomplete multi-view camera data. This paper presents SafeMap, a novel framework specifically designed to ensure accuracy even when certain camera views are missing. SafeMap integrates two key components: the Gaussian-based Perspective View Reconstruction (G-PVR) module and the Distillation-based Bird’s-Eye-View (BEV) Correction (D-BEVC) module. G-PVR leverages prior knowledge of view importance to dynamically prioritize the most informative regions based on the relationships among available camera views. Furthermore, D-BEVC utilizes panoramic BEV features to correct the BEV representations derived from incomplete observations. Together, these components facilitate comprehensive data reconstruction and robust HD map generation. SafeMap is easy to implement and integrates seamlessly into existing systems, offering a plug-and-play solution for enhanced robustness. Experimental results demonstrate that SafeMap significantly outperforms previous methods in both complete and incomplete scenarios, highlighting its superior performance and resilience.
APA
Hao, X., Kong, L., Yin, R., Wang, P., Zhang, J., Diao, Y. & Zhao, S.. (2025). SafeMap: Robust HD Map Construction from Incomplete Observations. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:22091-22102 Available from https://proceedings.mlr.press/v267/hao25b.html.

Related Material