We present MR-Net, a general architecture for multiresolution neural networks, and a framework for imaging applications based on this architecture. Our coordinate-based networks are continuous both in space and in scale as they are composed of multiple stages that progressively add finer details. Besides that, they are a compact and efficient representation. We show examples of multiresolution image representation and applications to texturemagnification, minification, and antialiasing. This document is the extended version of the paper [PNS+22]. It includes additional material that would not fit the page limitations of the conference track for publication.
@article{arxiv.2208.11813,
title = {Multiresolution Neural Networks for Imaging},
author = {Hallison Paz and Tiago Novello and Vinicius Silva and Luiz Schirmer and Guilherme Schardong and Fabio Chagas and Helio Lopes and Luiz Velho},
journal= {arXiv preprint arXiv:2208.11813},
year = {2022}
}