Generalized Rectifier Wavelet Covariance Models For Texture Synthesis

03/14/2022
by   Antoine Brochard, et al.
8

State-of-the-art maximum entropy models for texture synthesis are built from statistics relying on image representations defined by convolutional neural networks (CNN). Such representations capture rich structures in texture images, outperforming wavelet-based representations in this regard. However, conversely to neural networks, wavelets offer meaningful representations, as they are known to detect structures at multiple scales (e.g. edges) in images. In this work, we propose a family of statistics built upon non-linear wavelet based representations, that can be viewed as a particular instance of a one-layer CNN, using a generalized rectifier non-linearity. These statistics significantly improve the visual quality of previous classical wavelet-based models, and allow one to produce syntheses of similar quality to state-of-the-art models, on both gray-scale and color textures.

READ FULL TEXT

page 7

page 9

page 17

page 19

page 20

page 21

page 22

page 23

research
05/22/2021

Texture synthesis via projection onto multiscale, multilayer statistics

We provide a new model for texture synthesis based on a multiscale, mult...
research
07/24/2017

Wavelet Convolutional Neural Networks for Texture Classification

Texture classification is an important and challenging problem in many i...
research
07/22/2017

A survey of exemplar-based texture synthesis

Exemplar-based texture synthesis is the process of generating, from an i...
research
10/10/2014

Challenge IEEE-ISBI/TCB : Application of Covariance matrices and wavelet marginals

This short memo aims at explaining our approach for the challenge IEEE-I...
research
05/31/2016

Texture Synthesis Using Shallow Convolutional Networks with Random Filters

Here we demonstrate that the feature space of random shallow convolution...
research
11/15/2013

Periodicity Extraction using Superposition of Distance Matching Function and One-dimensional Haar Wavelet Transform

Periodicity of a texture is one of the important visual characteristics ...
research
11/22/2019

Maximum Entropy Models from Phase Harmonic Covariances

We define maximum entropy models of non-Gaussian stationary random vecto...

Please sign up or login with your details

Forgot password? Click here to reset