论文标题
可变形的PV-RCNN：通过学习变形改进3D对象检测
Deformable PV-RCNN: Improving 3D Object Detection with Learned Deformations
论文作者
论文摘要
我们提出可变形的PV-RCNN，这是一种基于高性能点云的3D对象检测器。当前，最先进的两阶段探测器使用的提案完善方法无法充分容纳不同的对象尺度，变化的点云密度，部分变形和混乱。我们提出了一个受2D可变形卷积网络启发的提案改进模块，该模块可以自适应地从存在信息内容的位置中自适应地收集实例特定功能。我们还提出了一种简单的上下文门控机制，该机制允许关键点为改进阶段选择相关的上下文信息。我们在Kitti数据集上显示最新结果。
We present Deformable PV-RCNN, a high-performing point-cloud based 3D object detector. Currently, the proposal refinement methods used by the state-of-the-art two-stage detectors cannot adequately accommodate differing object scales, varying point-cloud density, part-deformation and clutter. We present a proposal refinement module inspired by 2D deformable convolution networks that can adaptively gather instance-specific features from locations where informative content exists. We also propose a simple context gating mechanism which allows the keypoints to select relevant context information for the refinement stage. We show state-of-the-art results on the KITTI dataset.
