Many point-based 3D detectors adopt point-feature sampling strategies to drop some points for efficient inference. These strategies are typically based on fixed and handcrafted rules, making it difficult to handle complicated scenes. Different from them, we propose a Dynamic Ball Query (DBQ) network to adaptively select a subset of input points according to the input features, and assign the feature transform with a suitable receptive field for each selected point. It can be embedded into some state-of-the-art 3D detectors and trained in an end-to-end manner, which significantly reduces the computational cost. Extensive experiments demonstrate that our method can increase the inference speed by 30%-100% on KITTI, Waymo, and ONCE datasets. Specifically, the inference speed of our detector can reach 162 FPS on KITTI scene, and 30 FPS on Waymo and ONCE scenes without performance degradation. Due to skipping the redundant points, some evaluation metrics show significant improvements. Codes will be released at https://github.com/yancie-yjr/DBQ-SSD.
翻译:----
许多基于点的三维检测器采用点特征采样策略来放弃一些点以进行高效的推理。这些策略通常基于固定的和手工制定的规则,难以处理复杂的场景。不同于它们,我们提出了一种动态球查询(DBQ)网络,根据输入特征自适应地选择输入点的子集,并为每个选择的点分配适当的感受野进行特征变换。它可以嵌入一些最先进的三维检测器,并以端到端的方式进行训练,从而显著降低了计算成本。广泛的实验表明,我们的方法可以在KITTI、Waymo和ONCE数据集上将推理速度提高30%-100%。具体而言,在KITTI场景中,我们检测器的推理速度可以达到162 FPS,在Waymo和ONCE场景中为30 FPS,而无性能降级。由于跳过了冗余点,一些评估指标显示出显著的改进。代码将在https://github.com/yancie-yjr/DBQ-SSD发布。