Abstract
While point-based neural architectures have demonstrated their efficacy, the time-consuming sampler currently prevents them from performing real-time reasoning on scene-level point clouds. Existing methods attempt to overcome this issue by using random sampling strategy instead of the commonly-adopted farthest point sampling~(FPS), but at the expense of lower performance. So the effectiveness/efficiency trade-off remains under-explored. In this paper, we reveal the key to high-quality sampling is ensuring an even spacing between points in the subset, which can be naturally obtained through a grid. Based on this insight, we propose a hierarchical adaptive voxel-guided point sampler with linear complexity and high parallelization for real-time applications. Extensive experiments on large-scale point cloud detection and segmentation tasks demonstrate that our method achieves competitive performance with the most powerful FPS, at an amazing speed that is more than 100 times faster. This breakthrough in efficiency addresses the bottleneck of the sampling step when handling scene-level point clouds. Furthermore, our sampler can be easily integrated into existing models and achieves a 20$\sim$80\% reduction in runtime with minimal effort. The code will be available at this https URL
Abstract (translated)
点基神经网络架构已经证明了其有效性,但消耗时间的采样方法 currently prevent them from performing real-time reasoning on scene-level point clouds. 现有的方法试图通过使用随机采样策略而不是常见的最远点采样(FPS)来解决这一问题,但付出了性能下降的代价。因此,有效性/效率的权衡仍然未被深入研究。在本文中,我们揭示了高质量采样的关键,是确保子集中的点之间的even spacing,这可以通过网格自然获得。基于这一洞察力,我们提出了一种HierarchicalAdaptiveVOXel引导点采样方法,具有线性复杂度和高并行化,为实时应用而设计。在大规模点云检测和分割任务的实验中,证明了我们的方法能够与最强大的FPS竞争性能,并以惊人的速度超过100倍的速度运行。这种效率突破解决了处理场景级点云时采样步骤的瓶颈。此外,我们的采样方法可以轻松地融入现有的模型中,并以 minimal effort 实现20$\sim$80%的运行时减少。代码将在此httpsURL上可用。
URL
https://arxiv.org/abs/2305.14306