In this paper we demonstrate that the framework of nonlinear spectral decompositions based on total variation (TV) regularization is very well suited for image fusion as well as more general image manipulation tasks. The well-localized and edge-preserving spectral TV decomposition allows to select frequencies of a certain image to transfer particular features, such as wrinkles in a face, from one image to another. We illustrate the effectiveness of the proposed approach in several numerical experiments, including a comparison to the competing techniques of Poisson image editing, linear osmosis, wavelet fusion and Laplacian pyramid fusion. We conclude that the proposed spectral TV image decomposition framework is a valuable tool for semi- and fully-automatic image editing and fusion.
@article{arxiv.1703.08001,
title = {Nonlinear Spectral Image Fusion},
author = {Martin Benning and Michael Möller and Raz Z. Nossek and Martin Burger and Daniel Cremers and Guy Gilboa and Carola-Bibiane Schönlieb},
journal= {arXiv preprint arXiv:1703.08001},
year = {2017}
}
Comments
13 pages, 9 figures, submitted to SSVM conference proceedings 2017