Skip to yearly menu bar Skip to main content

In-Person Poster presentation / poster accept

DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection

Jinrong Yang · Lin Song · Songtao Liu · Weixin Mao · Zeming Li · Xiaoping Li · Hongbin Sun · Jian Sun · Nanning Zheng

MH1-2-3-4 #77

Keywords: [ Deep Learning and representational learning ]


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 reduce latency 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.

Chat is not available.