论文标题
3DSSD：基于点的3D单阶段对象检测器
3DSSD: Point-based 3D Single Stage Object Detector
论文作者
论文摘要
当前，基于体素的3D单阶段检测器有许多类型的单阶段方法，而基于点的单阶段方法仍然没有被逐渐置换。在本文中，我们首先提出一个基于点的3D单阶段对象检测器，称为3DSSD，在准确性和效率之间取得了良好的平衡。在此范式中，在所有现有基于点的方法中都是必不可少的所有UP采样层和改进阶段，都被放弃以降低大量计算成本。我们在缩减采样过程中提出了一种融合采样策略，以对较低的代表点进行检测。一个精致的盒子预测网络，包括候选生成层，具有3D中心分配策略的无锚回归头旨在满足我们对准确性和速度的需求。我们的范式是一个优雅的单阶段无锚框架，显示出与其他现有方法的极大优势。我们在广泛使用的Kitti数据集和更具挑战性的Nuscenes数据集上评估了3DSSD。我们的方法的表现优于所有基于体素的单阶段方法的大幅度，并且具有与两种基于点的方法相当的性能，其推理速度超过25 fps，比以前基于先进的点的方法快2倍。
Currently, there have been many kinds of voxel-based 3D single stage detectors, while point-based single stage methods are still underexplored. In this paper, we first present a lightweight and effective point-based 3D single stage object detector, named 3DSSD, achieving a good balance between accuracy and efficiency. In this paradigm, all upsampling layers and refinement stage, which are indispensable in all existing point-based methods, are abandoned to reduce the large computation cost. We novelly propose a fusion sampling strategy in downsampling process to make detection on less representative points feasible. A delicate box prediction network including a candidate generation layer, an anchor-free regression head with a 3D center-ness assignment strategy is designed to meet with our demand of accuracy and speed. Our paradigm is an elegant single stage anchor-free framework, showing great superiority to other existing methods. We evaluate 3DSSD on widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well, with inference speed more than 25 FPS, 2x faster than former state-of-the-art point-based methods.
