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3D检测器采用点特征采样策略丢弃部分点以实现高效推理。这些策略通常基于固定的手工规则，难以处理复杂场景。与它们不同，我们提出动态球查询（DBQ）网络，可根据输入特征自适应地选择输入点子集，并为每个选定点分配具有合适感受野的特征变换。该网络可嵌入当前最先进的3D检测器，并以端到端方式训练，显著降低计算成本。大量实验表明，我们的方法在KITTI、Waymo和ONCE数据集上可将推理速度提升30%-100%。具体而言，我们的检测器在KITTI场景中推理速度可达162 FPS，在Waymo和ONCE场景中达30 FPS，且性能无下降。由于跳过了冗余点，部分评估指标还呈现显著提升。代码将于https://github.com/yancie-yjr/DBQ-SSD 开源。