Type of Publication

Others

Date:

8 /

2023

Status

Published

DOI:

10.1016/j.cag.2023.05.014

MR-Net: Multiresolution sinusoidal neural networks

Featured in:

Computers & Graphics

Authors:

Hallison Paz, Daniel Perazzo, Tiago Novello, Guilherme Schardong, Luiz Schirmer, Vinícius da Silva, Daniel Yukimura, Fabio Chagas, Hélio Lopes and Luiz Velho

Abstract

We present MR-Net, a general architecture for multiresolution sinusoidal neural networks, and a framework for imaging applications based on this architecture. We extend sinusoidal networks, and we build an infrastructure to train networks to represent signals in multiresolution. Our coordinate-based networks, namely L-Net, M-Net, and S-Net, are continuous both in space and in scale as they are composed of multiple stages that progressively add finer details. Currently, band-limited coordinate networks (BACON) are able to represent signals at multiscale by limiting their Fourier spectra. However, this approach introduces artifacts leading to an image with a ringing effect. We show that MR-Net can represent more faithfully what is expected of sequentially applying low-pass filters in a high-resolution image. Our experiments on the Kodak Dataset show that MR-Net can reach comparable Peak Signal-to-Noise Ratio (PSNR) to other architectures, on image reconstruction, while needing fewer additional parameters for multiresolution. Along with MR-Net, we detail our architecture’s mathematical foundations and general ideas, and show examples of applications to texture magnification, minification, and antialiasing. Lastly, we compare our three MR-Net subclasses.

Citation
Hallison Paz, Daniel Perazzo, Tiago Novello, Guilherme Schardong, Luiz Schirmer, Vinícius da Silva, Daniel Yukimura, Fabio Chagas, Hélio Lopes and Luiz Velho (2023). MR-Net: Multiresolution sinusoidal neural networks. Computers & Graphics, 114, 387-400. DOI: 10.1016/j.cag.2023.05.014

Related Content

Post-Doc Researcher
Post-Doc Researcher
No tagged content to show
No tagged content to show
No tagged content to show

RECENT PUBLICATIONS

FLOWING: Implicit Neural Flows for Structure-Preserving Morphing

Authors: Arthur Bizzi; Matias Grynberg; Vitor Matias; Daniel Perazzo; João Paulo Lima; Luiz Velho; Nuno Gonçalves; João Pereira; Guilherme Schardong; Tiago Novello
Featured in: 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Adversarial Attack Challenge for Secure Face Recognition 2025

Authors: João Tremoço, Iurii Medvedev, Nuno Freitas, Andreia Costa, Diogo Nunes, Niklas Bunzel, Lukas Graner, Nicholas Göller, Lorenzo Pellegrini, Nicolò Di Domenico, Guido Borghi, Monson Verghese, Shruti Bhilare, Avik Hati, Miguel Lourenço, Nuno Gonçalves
Featured in: IEEE International Joint Conference on Biometrics (IJCB 2025)

VOIDFace: A Privacy-Preserving Multi-Network Face Recognition With Enhanced Security

Authors: Ajnas Muhammed; Iurii Medvedev; Nuno Gonçalves
Featured in: IEEE International Joint Conference on Biometrics (IJCB 2025)

suggested news

Paper accepted to IJCB 2025
Prof. Nuno and VIS Team successfully organizes IbPRIA...
Four papers presented @ IbPRIA 2025

RECENT PROJECTS

FACING2 – Face Image Understanding
VISUAL-ID – Unique Visual Identities in Graphics, Images and Faces
UniqueMark

Institute of Systems and Robotics Department of Electrical and Computers Engineering University of Coimbra