3D object detection is one of the most important tasks in autonomous driving and robotics. Our research focuses on tackling low efficiency issue of point-based methods on large-scale point clouds. Existing point-based methods adopt farthest point sampling (FPS) strategy for downsampling, which is computationally expensive in terms of inference time and memory consumption when the number of point cloud increases. In order to improve efficiency, we propose a novel Instance-Centroid Faster Point Sampling Module (IC-FPS) , which effectively replaces the first Set Abstraction (SA) layer that is extremely tedious. IC-FPS module is comprised of two methods, local feature diffusion based background point filter (LFDBF) and Centroid-Instance Sampling Strategy (CISS). LFDBF is constructed to exclude most invalid background points, while CISS substitutes FPS strategy by fast sampling centroids and instance points. IC-FPS module can be inserted to almost every point-based models. Extensive experiments on multiple public benchmarks have demonstrated the superiority of IC-FPS. On Waymo dataset, the proposed module significantly improves performance of baseline model and accelerates inference speed by 3.8 times. For the first time, real-time detection of point-based models in large-scale point cloud scenario is realized.

翻译：摘要：三维目标检测是自动驾驶与机器人领域最重要的任务之一。本研究聚焦于解决点云方法在大规模点云场景中的低效率问题。现有基于点云的方法采用最远点采样（FPS）策略进行降采样，随着点云数量增加，该策略在推理时间和内存消耗上计算开销巨大。为提升效率，我们提出了一种新型实例中心快速点采样模块（IC-FPS），该模块可有效替代计算极为繁琐的首个集合抽象（SA）层。IC-FPS模块由两种方法构成：基于局部特征扩散的背景点过滤方法（LFDBF）和中心实例采样策略（CISS）。其中，LFDBF用于剔除大多数无效背景点，而CISS通过快速采样中心点与实例点替代FPS策略。IC-FPS模块可嵌入几乎所有基于点云的模型中。在多个公开基准上的大量实验证明了IC-FPS的优越性。在Waymo数据集上，该模块显著提升基线模型性能，并将推理速度加速3.8倍。这是首次实现点云模型在大规模点云场景下的实时检测。