BriefGPT.xyz
Oct, 2020
训练数据生成网络：通过双层优化实现形状重建
Training Data Generating Networks: Linking 3D Shapes and Few-Shot Classification
HTML
PDF
Biao Zhang, Peter Wonka
TL;DR
提出了一种新的三维形状表示方法，用于从单个图像中重建三维形状。通过训练神经网络生成训练集，再利用元学习方法进行双层优化，建立了三维形状分析和少样本学习之间的联系。该方法结合了训练数据生成网络与双层优化算法，可以联合训练，提高了三维形状重建的标准基准上的性能。
Abstract
We propose a novel
3d shape representation
for 3d
shape reconstruction
from a single image. Rather than predicting a shape directly, we train a network to generate a training set which will be feed into another l
→