BriefGPT.xyz
Jul, 2020
基于形状先验变形的6D类别目标姿态与尺寸估计
Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation
HTML
PDF
Meng Tian, Marcelo H Ang Jr, Gim Hee Lee
TL;DR
本研究提出了一种基于深度学习的方法,通过创建有关先前学习类别形状先验信息的3D对象模型并推断出深度观测和3D模型之间的密集对应关系,使得能够从RGB-D图像中恢复未看见的物体实例的6D姿态和大小。
Abstract
We present a novel learning approach to recover the
6d poses
and
sizes
of unseen object instances from an
rgb-d image
. To handle the intra
→