Aerial Spectral Super-Resolution using Conditional Adversarial Networks
This work addresses the challenge of spectral super-resolution in aerial imagery for applications in remote sensing, but it is incremental as it adapts existing adversarial methods to a new dataset.
The paper tackles the problem of inferring spectral signatures from aerial imagery, which has low spatial resolution and high noise, by training a conditional adversarial network to map from trichromatic space to 31 spectral bands, achieving a baseline root mean square error of 2.48 on synthesized RGB test data.
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, aerial spectral images have low spatial resolution and suffer from higher noise interference. In this paper, we train a conditional adversarial network to learn an inverse mapping from a trichromatic space to 31 spectral bands within 400 to 700 nm. The network is trained on AeroCampus, a first of its kind aerial hyperspectral dataset. AeroCampus consists of high spatial resolution color images and low spatial resolution hyperspectral images (HSI). Color images synthesized from 31 spectral bands are used to train our network. With a baseline root mean square error of 2.48 on the synthesized RGB test data, we show that it is possible to generate spectral signatures in aerial imagery.