We present a simple and flexible object detection framework optimized for
autonomous driving. Building on the observation that point clouds in this
application are extremely sparse, we propose a practical pillar-based approach
to fix the imbalance issue caused by anchors. In particular, our algorithm
incorporates a cylindrical projection into multi-view feature learning,
predicts bounding box parameters per pillar rather than per point or per
anchor, and includes an aligned pillar-to-point projection module to improve
the final prediction. Our anchor-free approach avoids hyperparameter search
associated with past methods, simplifying 3D object detection while
significantly improving upon state-of-the-art.

本篇论文提出了一种适用于自动驾驶的简单灵活的物体检测框架，该框架基于车载点云数据的稀疏性质，通过柱状体进行多视角特征学习来解决过去方法因锚点不平衡带来的问题，采用一种新的适配柱状体的映射模块实现更精准的检测，而且该算法还避免了过去方法中涉及超参数搜索的问题，较大地提高了 3D 物体检测的准确率。