3D object detection in point clouds is a core component for modern robotics
and autonomous driving systems. A key challenge in 3D object detection comes
from the inherent sparse nature of point occupancy within the 3D scene. In this
paper, we propose Sparse Window Transformer (SWFormer ), a scalable and
accurate model for 3D object detection, which can take full advantage of the
sparsity of point clouds. Built upon the idea of window-based Transformers,
SWFormer converts 3D points into sparse voxels and windows, and then processes
these variable-length sparse windows efficiently using a bucketing scheme. In
addition to self-attention within each spatial window, our SWFormer also
captures cross-window correlation with multi-scale feature fusion and window
shifting operations. To further address the unique challenge of detecting 3D
objects accurately from sparse features, we propose a new voxel diffusion
technique. Experimental results on the Waymo Open Dataset show our SWFormer
achieves state-of-the-art 73.36 L2 mAPH on vehicle and pedestrian for 3D object
detection on the official test set, outperforming all previous single-stage and
two-stage models, while being much more efficient.

本文提出了一种针对 3D 目标检测的模型 Sparse Window Transformer（SWFormer），它能够充分利用点云数据的稀疏性，并通过 “桶” 技术对不同长度的稀疏窗口有效地进行处理。在 Multi-scale 特征融合和窗口偏移操作的基础上，作者还引入了新的体素扩散技术。最终，在 Waymo Open Dataset 上的实验结果表明，SWFormer 相比于所有先前的单阶段和两阶段模型，取得了最新的 73.36 L2 mAPH 表现，同时更加高效。