论文标题
DBQ-SSD：高效3D对象检测的动态球查询
DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection
论文作者
论文摘要
许多基于点的3D检测器采用点功能采样策略来提出一些分数以提高推断。这些策略通常基于固定和手工制作的规则，因此很难处理复杂的场景。与它们不同的是，我们提出了一个动态球查询（DBQ）网络，以根据输入特征自适应地选择输入点的子集，并为每个选定的点具有合适的接收场分配特征变换。它可以嵌入到一些最新的3D检测器中，并以端到端的方式进行训练，从而大大降低了计算成本。广泛的实验表明，我们的方法可以将Kitti，Waymo和一次数据集的推理速度提高30％-100％。具体来说，我们检测器的推理速度可以在Kitti场景上达到162 fps，在Waymo上可以达到30 fps，一旦场景而没有性能退化。由于跳过冗余点，一些评估指标显示出显着改善。代码将在https://github.com/yancie-yjr/dbq-ssd上发布。
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.
