3D object detectors usually rely on hand-crafted proxies, e.g., anchors or
centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel
features need to be densified and processed by dense prediction heads, which
inevitably costs extra computation. In this paper, we instead propose VoxelNext
for fully sparse 3D object detection. Our core insight is to predict objects
directly based on sparse voxel features, without relying on hand-crafted
proxies. Our strong sparse convolutional network VoxelNeXt detects and tracks
3D objects through voxel features entirely. It is an elegant and efficient
framework, with no need for sparse-to-dense conversion or NMS post-processing.
Our method achieves a better speed-accuracy trade-off than other mainframe
detectors on the nuScenes dataset. For the first time, we show that a fully
sparse voxel-based representation works decently for LIDAR 3D object detection
and tracking. Extensive experiments on nuScenes, Waymo, and Argoverse2
benchmarks validate the effectiveness of our approach. Without bells and
whistles, our model outperforms all existing LIDAR methods on the nuScenes
tracking test benchmark.

本文提出了一种名为 VoxelNext 的基于稀疏体素特征的完全稀疏 3D 目标检测方法，通过少量的推断即可检测和跟踪 3D 目标，它具有良好的速度 - 精度折衷，且不需后续的稀疏转密集转换或 NMS 后处理。实验证明，该方法能够在 nuScenes、Waymo 和 Argoverse2 基准上显著提高检测效果。