On scale-invariant properties in natural images and their simulations

01/27/2022
by   Maxim Koroteev, et al.
0

We study samples of natural images for which a set of statistical characteristics is computed and scale-invariant properties of samples are demonstrated computationally. Computations of the power spectrum are carried out and a power-law decaying power spectrum is observed on samples taken from van Hateren images of natural scenes. We propose a dynamic model to reproduce the observed slope in the power spectrum qualitatively. For two types of sources for this model the behaviour of power spectrum is investigated and scale-invariance confirmed numerically. We then discuss potential applications of scale-invariant properties of natural images.

READ FULL TEXT

page 4

page 6

page 7

research
08/09/2017

Statistics of Deep Generated Images

Here, we explore the low-level statistics of images generated by state-o...
research
06/19/2014

Why are images smooth?

It is a well observed phenomenon that natural images are smooth, in the ...
research
09/04/2019

Optimal translational-rotational invariant dictionaries for images

We provide the construction of a set of square matrices whose translates...
research
02/04/2015

Learning Local Invariant Mahalanobis Distances

For many tasks and data types, there are natural transformations to whic...
research
09/20/2011

Mixtures of conditional Gaussian scale mixtures applied to multiscale image representations

We present a probabilistic model for natural images which is based on Ga...
research
04/11/2022

Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data

Transfer learning for GANs successfully improves generation performance ...
research
10/20/2021

Analytic Correlation of Inflationary Potential to Power Spectrum Shape: Limits of Validity, and `No-Go' for Small Field Model Analytics

The primordial power spectrum informs the possible inflationary historie...

Please sign up or login with your details

Forgot password? Click here to reset