Multiresolution Neural Networks for Imaging

News

Abstract

MR-Net is a general architecture for multiresolution neural networks, and a framework for imaging applications. 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 and minification, and antialiasing.

Paper

Multiresolution Neural Networks for Imaging

Hallison Paz, Tiago Novello, Vinicius Silva, Guilherme Shardong, Luiz Schirmer, Fabio Chagas, Helio Lopes, Luiz Velho

description Paper (PDF, 3 MB)

description arXiv version

insert_comment BibTeX

Please send feedback and questions to Hallison Paz.

Citation

@inproceedings{paz2022mrnet,
		title = {Multiresolution Neural Networks for Imaging},
		author = {Hallison Paz and Tiago Novello and Vinicius Silva and Guilherme Shardong and 
			      Luiz Schirmer and Fabio Chagas and Helio Lopes and  Luiz Velho},
		booktitle = {Proceedings of SIBGRAPI},
		year = {2022},
		}
		

Acknowledgements