BriefGPT.xyz
Oct, 2015
训练卷积神经网络比较图像片段进行立体匹配
Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches
HTML
PDF
Jure Žbontar, Yann LeCun
TL;DR
本研究基于卷积神经网络为计算视差匹配的成本聚合，并针对KITTI2012、KITTI2015和Middlebury立体数据集对该方法进行了验证，结果表明其在所有三个数据集上优于其他方法。
Abstract
We present a method for extracting
depth information
from a rectified image pair. Our approach focuses on the first stage of many
stereo algorithms
: the matching cost computation. We approach the problem by learn
→