We present snapshot hyperspectral light field tomography (Hyper-LIFT), a highly efficient
method in recording a 5D (x, y, spatial coordinates; θ, φ, angular coordinates; λ, wavelength) …

Photo-realistic neural reconstruction and rendering of the human portrait are critical for
numerous VR/AR applications. Still, existing solutions inherently rely on multi-view capture …

Deep learning undoubtedly has had a huge impact on the computer vision community in
recent years. In light field imaging, machine learning-based applications have significantly …

We present tunable image projection spectrometry (TIPS), a Fourier-domain line-scan
spectral imager with a tunable compression ratio. Compared to state-of-the-art spatial …

In this work, spatio-spectrally coded multispectral light fields, as taken by a light field camera
with a spectrally coded microlens array, are investigated. For the reconstruction of the coded …

We present a novel method to reconstruct a spectral central view and its aligned disparity
map from spatio-spectrally coded light fields. Since we do not reconstruct an intermediate …

Hyperspectral imaging systems provide dense spectral information on the scene under
investigation by collecting data from a high number of contiguous bands of the …

Imaging systems capture light rays contain rich information, which can be described by the
plenoptic function,?(?,?,?,?,?,?,?)—where?,?,? represent spatial coordinates;?,? denote …

Real-time diagnosis of the radiative properties of participatory media, such as flames, is very
difficult due to their spatial and temporal complexity. In this paper, we propose a new method …

In light field imaging, one challenging task is to fuse the spatial and angular information with
spectral information. Existing methods for multi-modal and multi-spectral correspondence …