STD: Sparse-to-Dense 3D Object Detector for Point Cloud

Zetong Yang, Yanan Sun, Shu Liu, Xiaoyong Shen, Jiaya Jia; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 1951-1960

Abstract


We propose a two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD). The first stage is a bottom-up proposal generation network that uses raw point clouds as input to generate accurate proposals by seeding each point with a new spherical anchor. It achieves a higher recall with less computation compared with prior works. Then, PointsPool is applied for proposal feature generation by transforming interior point features from sparse expression to compact representation, which saves even more computation. In box prediction, which is the second stage, we implement a parallel intersection-over-union (IoU) branch to increase awareness of localization accuracy, resulting in further improved performance. We conduct experiments on KITTI dataset, and evaluate our method on 3D object and Bird's Eye View (BEV) detection. Our method outperforms other methods by a large margin, especially on the hard set, with 10+ FPS inference speed.

Related Material


[pdf]
[bibtex]
@InProceedings{Yang_2019_ICCV,
author = {Yang, Zetong and Sun, Yanan and Liu, Shu and Shen, Xiaoyong and Jia, Jiaya},
title = {STD: Sparse-to-Dense 3D Object Detector for Point Cloud},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}