We introduce RoScenes, the largest multi-view roadside perception dataset,
which aims to shed light on the development of vision-centric Bird's Eye View
(BEV) approaches for more challenging traffic scenes. The highlights of
RoScenes include significantly large perception area, full scene coverage and
crowded traffic. More specifically, our dataset achieves surprising 21.13M 3D
annotations within 64,000 $m^2$. To relieve the expensive costs of roadside 3D
labeling, we present a novel BEV-to-3D joint annotation pipeline to efficiently
collect such a large volume of data. After that, we organize a comprehensive
study for current BEV methods on RoScenes in terms of effectiveness and
efficiency. Tested methods suffer from the vast perception area and variation
of sensor layout across scenes, resulting in performance levels falling below
expectations. To this end, we propose RoBEV that incorporates feature-guided
position embedding for effective 2D-3D feature assignment. With its help, our
method outperforms state-of-the-art by a large margin without extra
computational overhead on validation set. Our dataset and devkit will be made
available at https://github.com/xiaosu-zhu/RoScenes.

在 RoScenes 中介绍了最大的多视角路边感知数据集，旨在为更具挑战性的交通场景的视觉中心 Bird's Eye View (BEV) 方法的发展提供参考。RoScenes 的亮点包括显着大的感知区域、完整的场景覆盖和拥挤的交通。通过 BEV-to-3D 联合注释流水线，我们以高效的方式收集了大量数据，达到了令人惊讶的 2113 万个 3D 注释。此外，我们还针对 RoScenes 上当前的 BEV 方法进行了全面的研究，考察了效果和效率。在大范围感知区域和场景间传感器布局变化的情况下，现有方法的性能未达到预期。因此，我们提出了 RoBEV，其结合了特征引导的位置嵌入，以实现有效的 2D-3D 特征分配。在验证集上，我们的方法在不增加额外计算负担的情况下，大幅领先于最先进方法。我们的数据集和开发工具包将在 https://github.com/xiaosu-zhu/RoScenes 上提供。