gwx18800155805 / gemap Goto Github PK

• (2023/12/7) We released the first version of GeMap (with pre-trained checkpoints and evaluation).
• (2023/12/7) GeMap is released on arXiv.

• Recent efforts have built strong baselines for online vectorized HD map construction task, however, shapes and relations of instances in urban road systems are still under-explored, such as parallelism, perpendicular, or rectangle-shape.

• As the ego vehicle moves, the shape of a specific instance or the relations between two instances will remain unchanged. To accurately represent such geometric features, invariance to rigid transformation is a fundamental property.

This work contributes from two perspectives:

• GeMap achieves new state-of-the-art performance on the NuScenes and Argoverse 2 datasets. Remarkably, it reaches a 71.8% mAP on the large-scale Argoverse 2 dataset, outperforming MapTR V2 by +4.4% and surpassing the 70% mAP threshold for the first time.
• GeMap end-to-end learns Euclidean shapes and relations of map instances beyond basic perception. Specifically, we design a geometric loss based on angle and distance clues, which is robust to rigid transformations. We also decouple self-attention to independently handle Euclidean shapes and relations.

* All models are trained on 8 NVIDIA RTX3090 GPUs. The speed (Frames Per Second, FPS) is evaluated on a single 3090 GPU.

GeMap exhibits more robust predictions in occluded and rotated scenarios, especially under rainy weather conditions.

• Installation
• Prepare Dataset
• Train and Eval
• Visualization

• Merge and clean up dataset pipelines.
• Add LiDAR support to all configurations.
• Try more backbones on Argoverse 2.

GeMap is based on mmdetection3d. It is also greatly inspired by the following outstanding contributions to the open-source community: LSS, GKT, Swin-Transformer, VoVNet, BEVFormer, MapTR, BeMapNet, HDMapNet.

If the paper and code help your research, please kindly cite:

@article{zhang2023online,
  title={Online Vectorized HD Map Construction using Geometry},
  author={Zhang, Zhixin and Zhang, Yiyuan and Ding, Xiaohan and Jin, Fusheng and Yue, Xiangyu},
  journal={arXiv preprint arXiv:2312.03341},
  year={2023}
}