Multiresolution Neural Networks for Imaging

Hallison Paz, Tiago Novello, Vinícius da Silva, Guilherme G. Schardong, Luiz Schirmer, Fabio Chagas, Hélio Lopes, Luiz Velho

Abstract: 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 texture magnification, minification, and antialiasing.