BriefGPT.xyz
Dec, 2017
利用条件对抗网络进行空中光谱超分辨率
Aerial Spectral Super-Resolution using Conditional Adversarial Networks
HTML
PDF
Aneesh Rangnekar, Nilay Mokashi, Emmett Ientilucci, Christopher Kanan, Matthew Hoffman
TL;DR
本研究旨在应用条件对抗网络从空中高光谱数据推断出地面自然图像的光谱特征，通过使用31个光谱波段合成来自高光谱数据的RGB彩色图像训练网络，取得了2.48的最佳均方根误差，表明可以在空中图像中生成光谱特征。
Abstract
Inferring
spectral signatures
from ground based natural images has acquired a lot of interest in applied deep learning. In contrast to the spectra of
ground based images
,
→