通过动态剪枝提升多帧点云感知，大幅增加可用帧数而无额外计算开销。
Efficient 3D Perception on Multi-Sweep Point Cloud with Gumbel Spatial Pruning
- 提出基于Gumbel的动态点云剪枝方法，自动识别并移除冗余点。
- 将点云帧数从10帧提升至40帧，显著提高检测与分割精度。
- 可无缝集成到现有网络，适合自动驾驶等需要长时序感知场景。
本文研究户外环境中的点云感知问题。现有方法在远距离或遮挡物体识别上受限于点云稀疏性。本文发现，累积多个连续时间点云帧可显著改善感知准确率，但计算成本随之上升，制约了大量帧的使用。我们观察到累积点云中存在大量冗余点，去除这些点对感知性能影响极小。为此，提出一种简单有效的Gumbel空间剪枝（GSP）层，通过端到端学习实现动态点采样。该层与网络其他模块解耦，可无缝嵌入现有点云架构。在不增加计算开销的前提下，将点云帧数从常见的10帧提升至40帧，显著增强感知性能。例如，在nuScenes 3D目标检测和BEV地图分割任务中，该剪枝策略有效提升了多个3D感知基线方法的表现。
原文摘要 · Abstract (English)
This paper studies point cloud perception within outdoor environments. Existing methods face limitations in recognizing objects located at a distance or occluded, due to the sparse nature of outdoor point clouds. In this work, we observe a significant mitigation of this problem by accumulating multiple temporally consecutive point cloud sweeps, resulting in a remarkable improvement in perception accuracy. However, the computation cost also increases, hindering previous approaches from utilizing a large number of point cloud sweeps. To tackle this challenge, we find that a considerable portion of points in the accumulated point cloud is redundant, and discarding these points has minimal impact on perception accuracy. We introduce a simple yet effective Gumbel Spatial Pruning (GSP) layer that dynamically prunes points based on a learned end-to-end sampling. The GSP layer is decoupled from other network components and thus can be seamlessly integrated into existing point cloud network architectures. Without incurring additional computational overhead, we increase the number of point cloud sweeps from 10, a common practice, to as many as 40. Consequently, there is a significant enhancement in perception performance. For instance, in nuScenes 3D object detection and BEV map segmentation tasks, our pruning strategy improves several 3D perception baseline methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。