论文标题
基于视觉的不均衡的BEV表示学习，具有极地栅格化和表面估计
Vision-based Uneven BEV Representation Learning with Polar Rasterization and Surface Estimation
论文作者
论文摘要
在这项工作中，我们为基于视觉的不均衡的BEV表示学习提出了PolarBev。为了适应摄像机成像的预先处理效果，我们在角度和径向上栅格化bev空间，并引入极性嵌入分解，以模拟极性网格之间的关联。极性网格被重新排列到类似阵列的常规表示，以进行有效的处理。此外，要确定2到3D对应关系，我们根据假设平面迭代更新BEV表面，并采用基于高度的特征转换。 PolarBev在单个2080TI GPU上保持实时推理速度，并且在BEV语义分割和BEV实例分割方面都胜过其他方法。展示彻底的消融以验证设计。该代码将以\ url {https://github.com/superz-liu/polarbev}发布。
In this work, we propose PolarBEV for vision-based uneven BEV representation learning. To adapt to the foreshortening effect of camera imaging, we rasterize the BEV space both angularly and radially, and introduce polar embedding decomposition to model the associations among polar grids. Polar grids are rearranged to an array-like regular representation for efficient processing. Besides, to determine the 2D-to-3D correspondence, we iteratively update the BEV surface based on a hypothetical plane, and adopt height-based feature transformation. PolarBEV keeps real-time inference speed on a single 2080Ti GPU, and outperforms other methods for both BEV semantic segmentation and BEV instance segmentation. Thorough ablations are presented to validate the design. The code will be released at \url{https://github.com/SuperZ-Liu/PolarBEV}.
