Stream Query Denoising for Vectorized HD-mAP Construction
Abstract
This paper introduces the Stream Query Denoising (SQD) strategy, a novel and general approach for high-definition map (HD-map) construction. SQD is designed to improve the modeling capability of map elements by learning temporal consistency. Specifically, SQD involves the process of denoising the queries, which are generated by the noised ground truth of the previous frame. This process aims to reconstruct the ground truth of the current frame during training. Our method can be applied to both static and temporal methods, showing the great effectiveness of SQD strategy. Extensive experiments on nuScenes and Argoverse2 show that our framework achieves superior performance, compared to other existing methods across all settings. Code will be available here.
Cite
Text
Wang et al. "Stream Query Denoising for Vectorized HD-mAP Construction." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72655-2_12Markdown
[Wang et al. "Stream Query Denoising for Vectorized HD-mAP Construction." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/wang2024eccv-stream/) doi:10.1007/978-3-031-72655-2_12BibTeX
@inproceedings{wang2024eccv-stream,
title = {{Stream Query Denoising for Vectorized HD-mAP Construction}},
author = {Wang, Shuo and Jia, Fan and Mao, Weixin and Liu, Yingfei and Zhao, Yucheng and Chen, Zehui and Wang, Tiancai and Zhang, Chi and Zhang, Xiangyu and Zhao, Feng},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-72655-2_12},
url = {https://mlanthology.org/eccv/2024/wang2024eccv-stream/}
}