BriefGPT.xyz
Jun, 2020
H3DNet:使用混合几何基元进行3D目标检测
H3DNet: 3D Object Detection Using Hybrid Geometric Primitives
HTML
PDF
Zaiwei Zhang, Bo Sun, Haitao Yang, Qixing Huang
TL;DR
H3DNet是一个用于物体检测和识别的卷积神经网络,通过预测一组混合的几何图元,即BB中心,BB面中心和BB边缘中心以实现更准确的物体边界框检测,并利用匹配和细化模块将物体边界框分类为检测到的对象并对其几何参数进行微调。
Abstract
We introduce
h3dnet
, which takes a colorless 3D point cloud as input and outputs a collection of oriented object
bounding boxes
(or BB) and their semantic labels. The critical idea of
→