The goal of Spectral Edge Image Fusion is to map a low-dimensional guide image so that its gradient structure matches that present in a higher dimensional image of the same scene with the additional constraint that the ‘colour’ aspect of the guide is approximately preserved. Applications of spectral edge fusion include mapping RGB+NIR to RGB and visualising remote sensing data.

This presentation is part of Minisymposium “MS45 - Mathematical techniques for bad visibility restoration”
organized by: Javier Vazquez-Corral (Information and Communication Technologies Department, Universitat Pompeu Fabra) .

Authors:

Graham Finlayson (School of Computing Sciences, University of East Anglia, Norwich Research Park)

Keywords:

colour, computer vision, fusion, image enhancement, image reconstruction, image representation, nonlinear optimization, partial differential equation models, structure tensor