The efficient use of nutrients by plants can significantly improve the economic profitability
and environmental sustainability of agricultural enterprises. Near infrared spectroscopy …

Coded aperture snapshot spectral imaging (CASSI) is an effective tool to capture real-world
3D hyperspectral images. While a number of existing work has been conducted for …

We propose the l-net, which reconstructs hyperspectral images (eg, with 24 spectral
channels) from a single shot measurement. This task is usually termed snapshot …

Hyperspectral recovery from a single RGB image has seen a great improvement with the
development of deep convolutional neural networks (CNNs). In this paper, we propose two …

Multi-spectral imaging is a fundamental tool characterizing the constituent energy of scene
radiation. However, current multi-spectral video cameras cannot scale up beyond megapixel …

Snapshot compressive imaging (SCI) systems have been developed to capture high-
dimensional (> 3) signals using low-dimensional off-the-shelf sensors, ie, mapping multiple …

We present a novel hyperspectral image reconstruction algorithm, which overcomes the
long-standing tradeoff between spectral accuracy and spatial resolution in existing …

Regularization is a fundamental technique to solve an ill-posed optimization problem
robustly and is essential to reconstruct compressive hyperspectral images. Various hand …

This paper presents a unified deep learning framework to recover hyperspectral images
from spectrally undersampled projections. Specifically, we investigate two kinds of …

Multispectral cameras collect image data with a greater number of spectral channels than
traditional trichromatic sensors, thus providing spectral information at a higher level of detail …