Search Results for author:
Found 3 papers, 0 papers with code
SDAT: Sub-Dataset Alternation Training for Improved Image Demosaicing
In data centric approaches, such as deep learning, the distribution of the dataset used for training can impose a bias on the networks' outcome.
Nonlinear Spectral Image Fusion
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.
Flows Generating Nonlinear Eigenfunctions
We introduce two flows: a forward flow and an inverse flow; for which the steady state solution is a nonlinear eigenfunction.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
