Horoma AI inc.

Published purpose

Super resolution involves synthetically increasing the resolution of gridded data beyond their native resolution. Typically, this is done using interpolation schemes (linear, non-linear), which estimate sub-grid-scale values from neighbouring data, and perform the same operation everywhere regardless of the large-scale context, or by requiring a network of radars with overlapping fields of view. Conceptually, a neural network may be able to learn relations between large-scale reflectance features and the associated sub-pixel-scale variability and outperform interpolation schemes. The project aims to use data fusion (various sources) to provide for super resolution of RADAR and multi-spectral data.