The goal of spectral imaging is to capture the spectral signature of a target. Traditional
scanning method for spectral imaging suffers from large system volume and low image …

This paper reviews the third biennial challenge on spectral reconstruction from RGB images,
ie, the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB …

Existing leading methods for spectral reconstruction (SR) focus on designing deeper or
wider convolutional neural networks (CNNs) to learn the end-to-end mapping from the RGB …

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 …

Modern hyperspectral imaging systems produce huge datasets potentially conveying a great
abundance of information; such a resource, however, poses many challenges in the …

Spectral super-resolution (sSR) is a very important technique to obtain hyperspectral images
from only RGB images, which can effectively overcome the high acquisition cost and low …

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 …

This paper reviews the second challenge on spectral reconstruction from RGB images, ie,
the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image …

With climate change and ever-increasing population growth, the pace of varietal
development needs to be accelerated in order to feed a population of 10 billion by 2050 …

Hyperspectral imaging is an essential imaging modality for a wide range of applications,
especially in remote sensing, agriculture, and medicine. Inspired by existing hyperspectral …