Innovative Non-parametric Texture Synthesis via Patch Permutations

نویسنده

  • Ryan Webster
چکیده

In this work, we present a non-parametric texture synthesis algorithm capable of producing plausible images without copying large tiles of the exemplar. We focus on a simple synthesis algorithm, where we explore two patch match heuristics; the well known Bidirectional Similarity (BS) measure and a heuristic that finds near permutations using the solution of an entropy regularized optimal transport (OT) problem. Innovative synthesis is achieved with a small patch size, where global plausibility relies on the qualities of the match. For OT, less entropic regularization also meant near permutations and more plausible images. We examine the tile maps of the synthesized images, showing that they are indeed novel superpositions of the input and contain few or no verbatim copies. Synthesis results are compared to a statistical method, namely a random convolutional network. We conclude by remarking simple algorithms using only the input image can synthesize textures decently well and call for more modest approaches in future algorithm design.

برای دانلود رایگان 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

Texture Synthesis via a Non-parametric Markov Random Field

In this paper we present a non-causal non-parametric multiscale Markov random field (MRF) texture model that is capable of synthesising a wide variety of textures. The textures that this model is capable of synthesising vary from the highly structured to the stochastic type and include those found in the Brodatz album of textures. The texture model uses Parzen estimation to estimate the conditi...

متن کامل

Patch-Based Texture Edges and Segmentation

A novel technique for extracting texture edges is introduced. It is based on the combination of two ideas: the patch-based approach, and non-parametric tests of distributions. Our method can reliably detect texture edges using only local information. Therefore, it can be computed as a preprocessing step prior to segmentation, and can be very easily combined with parametric deformable models. Th...

متن کامل

Image Enhancement Techniques by Texture Synthesis

It has been observed that stretching of the Image may damage the clarity in many Image Processing applications. Edge and Textures are among the most important features of an image. They have however very different characteristics, suggestions that they should be enhanced using different techniques. For edges, we propose a sobel techniques and finding the edge of all objects .For textures we hav...

متن کامل

Wavelet Based Texture Synthesis

This paper presents a new algorithm for synthesising image texture. Texture synthesis is an important process in image post-production. The best previous approaches have used non-parametric methods for synthesising texture. Unfortunately, these methods generally suffer from high computational cost and difficulty in handling scale in the synthesis process. This paper introduces a new idea of usi...

متن کامل

Parametric quality assessment of synthesized textures

In this paper, we present the results of a study designed to investigate the visual factors which contribute to the perceived quality of synthesized textures. A psychophysical experiment was performed in which subjects rated the quality of textures synthesized from a variety of modern texture-synthesis algorithms. The ratings were given in terms of how well each synthesized texture represented ...

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

عنوان ژورنال:
  • CoRR

دوره abs/1801.04619  شماره 

صفحات  -

تاریخ انتشار 2018