3D-CenterNet: 3D object detection network for point clouds with center estimation priority

作者：

Highlights：

• We propose the center regression module to estimate centers' locations of objects only with point cloud.

• We propose the new single-stage 3D object detector, 3D-CenterNet, which emphasizes the object centers’ regressions.

• The results evaluated on the open datasets show that our framework is superior to the existing single-stage methods.

摘要

•We propose the center regression module to estimate centers' locations of objects only with point cloud.•We propose the new single-stage 3D object detector, 3D-CenterNet, which emphasizes the object centers’ regressions.•The results evaluated on the open datasets show that our framework is superior to the existing single-stage methods.

论文关键词：3D object detection,Point cloud,Deep learning

论文评审过程：Received 3 July 2020, Revised 5 January 2021, Accepted 5 February 2021, Available online 11 February 2021, Version of Record 18 February 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107884