BriefGPT.xyz
Oct, 2018
可微分点云的无监督形状和姿态学习
Unsupervised Learning of Shape and Pose with Differentiable Point Clouds
HTML
PDF
Eldar Insafutdinov, Alexey Dosovitskiy
TL;DR
该研究使用卷积神经网络训练能够从单个图像预测出物体的3D形状和相机姿态的模型，并通过一组pose预测器进行姿势模糊处理，并利用可微分3D点云投影技术来获取高保真度的形状模型。
Abstract
We address the problem of learning accurate
3d shape
and
camera pose
from a collection of unlabeled category-specific images. We train a
convolut
→