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 …

Gaussian scale spaces are a cornerstone of signal representation and processing, with
applications in filtering, multiscale analysis, anti-aliasing, and many more. However …

The real world exhibits rich structure and detail across many scales of observation. It is
difficult, however, to capture and represent a broad spectrum of scales using ordinary …

Implicit neural representations (INRs) have emerged as a promising framework for
representing signals in low-dimensional spaces. This survey reviews the existing literature …

Digital terrain models (DTMs) are pivotal in remote sensing cartography and landscape
management requiring accurate surface representation and topological information …

In this work, we investigate the structure and representation capacity of sinusoidal MLPs-
multilayer perceptron networks that use sine as the activation function. These neural …

We explore sinusoidal neural networks to represent periodic tileable textures. Our approach
leverages the Fourier series by initializing the first layer of a sinusoidal neural network with …

In the article the usage of neural networks for increasing image rendering efficiency was
analyzed. The main characteristics of the most popular neural networks architectures are …

Multiresolution Neural Networks for Multiscale Signal Representation Page 1
Multiresolution Neural Networks for Multiscale Signal Representation Luiz Velho, Hallison …

We present an implicit neural representation (INR) to describe periodic signals in neural
rendering. We aim to encode attribute functions through a periodic neural network 𝑓: R𝑛→ …