Seeing Implicit Neural Representations as Fourier Series

09/01/2021
by   Nuri Benbarka, et al.
7

Implicit Neural Representations (INR) use multilayer perceptrons to represent high-frequency functions in low-dimensional problem domains. Recently these representations achieved state-of-the-art results on tasks related to complex 3D objects and scenes. A core problem is the representation of highly detailed signals, which is tackled using networks with periodic activation functions (SIRENs) or applying Fourier mappings to the input. This work analyzes the connection between the two methods and shows that a Fourier mapped perceptron is structurally like one hidden layer SIREN. Furthermore, we identify the relationship between the previously proposed Fourier mapping and the general d-dimensional Fourier series, leading to an integer lattice mapping. Moreover, we modify a progressive training strategy to work on arbitrary Fourier mappings and show that it improves the generalization of the interpolation task. Lastly, we compare the different mappings on the image regression and novel view synthesis tasks. We confirm the previous finding that the main contributor to the mapping performance is the size of the embedding and standard deviation of its elements.

READ FULL TEXT

page 1

page 5

page 6

page 8

research
06/18/2020

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

We show that passing input points through a simple Fourier feature mappi...
research
12/23/2021

FourierMask: Instance Segmentation using Fourier Mapping in Implicit Neural Networks

We present FourierMask, which employs Fourier series combined with impli...
research
05/27/2020

Approximating periodic functions and solving differential equations using a novel type of Fourier Neural Networks

Recently, machine learning tools in particular neural networks have been...
research
02/08/2019

Fourier Neural Networks: A Comparative Study

We review neural network architectures which were motivated by Fourier s...
research
03/27/2018

Periodic Fourier representation of boolean functions

In this work, we consider a new type of Fourier-like representation of b...
research
07/05/2022

Learning Local Implicit Fourier Representation for Image Warping

Image warping aims to reshape images defined on rectangular grids into a...
research
12/02/2022

QFF: Quantized Fourier Features for Neural Field Representations

Multilayer perceptrons (MLPs) learn high frequencies slowly. Recent appr...

Please sign up or login with your details

Forgot password? Click here to reset