DeepAI AI Chat
Log In Sign Up

Texture Synthesis Using Shallow Convolutional Networks with Random Filters

by   Ivan Ustyuzhaninov, et al.

Here we demonstrate that the feature space of random shallow convolutional neural networks (CNNs) can serve as a surprisingly good model of natural textures. Patches from the same texture are consistently classified as being more similar then patches from different textures. Samples synthesized from the model capture spatial correlations on scales much larger then the receptive field size, and sometimes even rival or surpass the perceptual quality of state of the art texture models (but show less variability). The current state of the art in parametric texture synthesis relies on the multi-layer feature space of deep CNNs that were trained on natural images. Our finding suggests that such optimized multi-layer feature spaces are not imperative for texture modeling. Instead, much simpler shallow and convolutional networks can serve as the basis for novel texture synthesis algorithms.


page 3

page 4

page 5

page 7


Texture Synthesis Using Convolutional Neural Networks

Here we introduce a new model of natural textures based on the feature s...

A survey of exemplar-based texture synthesis

Exemplar-based texture synthesis is the process of generating, from an i...

On Random Weights for Texture Generation in One Layer Neural Networks

Recent work in the literature has shown experimentally that one can use ...

A Generative Model of Natural Texture Surrogates

Natural images can be viewed as patchworks of different textures, where ...

Stochastic Texture Difference for Scale-Dependent Data Analysis

This article introduces the Stochastic Texture Difference method for ana...

Texture Modeling with Convolutional Spike-and-Slab RBMs and Deep Extensions

We apply the spike-and-slab Restricted Boltzmann Machine (ssRBM) to text...

Generalized Rectifier Wavelet Covariance Models For Texture Synthesis

State-of-the-art maximum entropy models for texture synthesis are built ...