A Generative Model of Natural Texture Surrogates

نویسندگان

  • Niklas Ludtke
  • Debapriya Das
  • Lucas Theis
  • Matthias Bethge
چکیده

Natural images can be seen as patchworks of different textures for which local image statistics are roughly stationary within confined regions but otherwise can be highly diverse. In order to model the natural variety of textures, we sampled 64×64 patches of homogeneous textures from a large image database and described each patch by a set of texture parameters obtained with a popular texture algorithm. Texture variations across natural images can thus be expressed by the empirical joint distribution of the texture parameters. After suitable post-processing, we were able to fit this distribution with a multivariate Gaussian. Sampling from the model, one obtains random vectors that can be back-transformed into texture parameters from which new textures can be synthesized. These generated textures share with natural images not only the characteristics of the second-order statistics (power spectrum) but also resemble higher-order image correlations to considerable extent. Thus, we have devised a generative model of natural texture surrogates with which we can generate fully controlled ensembles of complex stimuli useful for probing the visual system for perceptually important high-order correlations of natural images. We demonstrate the descriptive power of our model by achieving state-of-the-art compression results based on texture synthesis using a simple quantization scheme of the texture coefficients. In addition, we demonstrate how our approach can be useful for evaluating the descriptive power of generative models of natural images. ar X iv :1 50 5. 07 67 2v 1 [ cs .C V ] 2 8 M ay 2 01 5

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

HEESS et al.: LEARNING GENERATIVE TEXTURE MODELS WITH EXTENDED FOES 1 Learning generative texture models with extended Fields-of-Experts

We evaluate the ability of the popular Field-of-Experts (FoE) to model structure in images. As a test case we focus on modeling synthetic and natural textures. We find that even for modeling single textures, the FoE provides insufficient flexibility to learn good generative models – it does not perform any better than the much simpler Gaussian FoE. We propose an extended version of the FoE (all...

متن کامل

Probabilistic Discrete Mixtures Colour Texture Models

A new generative multispectral texture model based on discrete distribution mixtures is introduced. Statistical texture properties are represented by a discrete distribution mixture of product components. A natural colour or multispectral texture is spectrally factorized and discrete mixtures models are learned and used to synthesize single orthogonal monospectral components. Texture synthesis ...

متن کامل

Texture Synthesis Using Convolutional Neural Networks

Here we introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition. Samples from the model are of high perceptual quality demonstrating the generative power of neural networks trained in a purely discriminative fashion. Within the model, textures are represented by the correlations between feature maps in several layer...

متن کامل

A study on the accuracy of motion tracking of thoracic tumors at radiotherapy with external surrogates

Introduction: In radiotherapy with external surrogates, exact information of tumor position is one of the key factors that improves treatment delivery. Many dynamic tumors in thorax region of patient move mainly due to respiration and are known as intra-fractional motion error that must be compensated, as well. One of clinical strategy is using Stereotactic Body Radiation Thera...

متن کامل

GANosaic: Mosaic Creation with Generative Texture Manifolds

This paper presents a novel framework for generating texture mosaics with convolutional neural networks. Our method is called GANosaic and performs optimization in the latent noise space of a generative texture model, which allows the transformation of a content image into a mosaic exhibiting the visual properties of the underlying texture manifold. To represent that manifold, we use a state-of...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1505.07672  شماره 

صفحات  -

تاریخ انتشار 2015