Texture Synthesis Algorithm Research Articles

Efros and Freeman Image Quilting Algorithm for Texture Synthesis

Exemplar-based texture synthesis is defined as the process of generating, from an input texture sample, new texture images that are perceptually equivalent to the input. Efros and Freeman's method is a non-parametric patch-based method which computes an output texture image by quilting together patches taken from the input sample. The main innovation of their work relies in the stitching technique which significantly reduces the transition effect between patches. In this paper, we propose a detailed analysis and implementation of their work. We provide a complete mathematical description of the linear programing problem used for the quilting step as well as implementation details. Additionally we propose a partially parallel version of the quilting technique. https://doi.org/10.5201/ipol.2017.171

基于梯度的块尺寸自适应Wang Tiles纹理合成算法

基于梯度的块尺寸自适应Wang Tiles纹理合成算法

Animating pictures of water scenes using video retrieval

We present a system to quickly and easily create an animation of water scenes in a single image. Our method relies on a database of videos of water scenes and video retrieval technique. Given an input image, alpha masks specifying regions of interest, and sketches specifying flow directions, our system first retrieves appropriate video candidates from the database and create the candidate animations for each region of interest as the composite of the input image and the retrieved videos: this process spends less than one minute by taking advantage of parallel distributed processing. Our system then allows the user to interactively control the speed of the desired animation and select the appropriate animation. After selecting the animation for all the regions, the resulting animation is completed. Finally, the user optionally applies a texture synthesis algorithm to recover the appearance of the input image. We demonstrate that our system allows the user to create a variety of animations of water scenes.

Summary Statistics and Material Categorization in the Visual Periphery

Material categorization from natural texture images proceeds quickly and accurately, supporting a number of visual and motor behaviors. In real-world settings, mechanisms for material categorization must function effectively based on the input from foveal vision, where image representation is high fidelity, and the input from peripheral vision, which is comparatively impoverished. What features support successful material categorization in the visual periphery, given the known reductions in acuity, contrast sensitivity, and other lossy transforms that reduce the fidelity of image representations? In general, the visual features that support material categorization remain largely unknown, but recent work suggests that observers’ abilities in a number of tasks that depend on peripheral vision can be accounted for by assuming that the visual system has access to only summary statistics (texture-like descriptors) of image structure. We therefore hypothesized that a model of peripheral vision based on the Portilla-Simoncelli texture synthesis algorithm might account for material categorization abilities in the visual periphery. Using natural texture images and synthetic images made from these stimuli, we compared performance across material categories to determine whether observer performance with natural inputs could be predicted by their performance with synthetic images that reflect the constraints of a texture code.

Multi-scale label-map extraction for texture synthesis

Texture synthesis is a well-established area, with many important applications in computer graphics and vision. However, despite their success, synthesis techniques are not used widely in practice because the creation of good exemplars remains challenging and extremely tedious. In this paper, we introduce an unsupervised method for analyzing texture content across multiple scales that automatically extracts good exemplars from natural images. Unlike existing methods, which require extensive manual tuning, our method is fully automatic. This allows the user to focus on using texture palettes derived from their own images, rather than on manual interactions dictated by the needs of an underlying algorithm. Most natural textures exhibit patterns at multiple scales that may vary according to the location (non-stationarity). To handle such textures many synthesis algorithms rely on an analysis of the input and a guidance of the synthesis. Our new analysis is based on a labeling of texture patterns that is both (i) multi-scale and (ii) unsupervised -- that is, patterns are labeled at multiple scales, and the scales and the number of labeled clusters are selected automatically. Our method works in two stages. The first builds a hierarchical extension of superpixels and the second labels the superpixels based on random walk in a graph of similarity between superpixels and a nonnegative matrix factorization. Our label-maps provide descriptors for pixels and regions that benefit state-of-the-art texture synthesis algorithms. We show several applications including guidance of non-stationary synthesis, content selection and texture painting. Our method is designed to treat large inputs and can scale to many megapixels. In addition to traditional exemplar inputs, our method can also handle natural images containing different textured regions.

A Montage Approach to Sound Texture Synthesis

Sound texture synthesis has applications in creating audio scenes for film and video games. In this paper, a novel algorithm for sound texture synthesis is presented. The goal of this algorithm is to produce new examples of a given sampled texture, the synthesized textures being of any desired duration. The algorithm is based on a montage approach to synthesis in that the original sample is cut into small pieces, referred to as atoms, and these atoms are concatenated together in a new sequence, preserving certain structures of the original texture. The sequence modelling of the atoms has two levels: atoms are concatenated to create segments and segments are concatenated, based on their history, to create textures. This approach deals with problems of repetition associated with sampling based sound texture synthesis techniques. Listening tests show that the results of the synthesis are very promising for a broad range of textures, including quasi-periodic and more random textures.

A Conditional Multiscale Locally Gaussian Texture Synthesis Algorithm

Exemplar-based texture synthesis is defined as the process of generating, from an input texture sample, new texture images that are perceptually equivalent to the input. In the present work, we model texture self-similarity with conditional Gaussian distributions in the patch space in order to extend the use of stitching techniques. Then, a multiscale texture synthesis algorithm is introduced, where texture patches are modeled at each scale as spatially variable Gaussian vectors in the patch space. The Gaussian distribution for each patch is inferred from the set of its nearest neighbors in the patch space obtained from the input sample. This approach is tested over several real and synthetic texture images, and its results show the effectiveness of the proposed technique for a wide range of textures.

Exemplar-based image inpainting using svd-based approximation matrix and multi-scale analysis

Reconstruction of images by digital inpainting is an active field of research and such algorithms are, in fact, now widely used. In conventional methods, a texture synthesis algorithm is used for f...

Texture Synthesis Using the Structure Tensor.

This paper proposes a two-stage texture synthesis algorithm. At the first stage, a structure tensor map carrying information about the local orientation is synthesized from the exemplar's data and used at the second stage to constrain the synthesis of the texture. Keeping in mind that the algorithm should be able to reproduce as faithfully as possible the visual aspect, statistics, and morphology of the input sample, the method is tested on various textures and compared objectively with existing methods, highlighting its strength in successfully synthesizing the output texture in many situations where traditional algorithms fail to reproduce the exemplar's patterns. The promising results pave the way towards the synthesis of accurately large and multi-scale patterns as it is the case for carbon material samples showing laminar structures, for example.

Inverse texture synthesis in wavelet packet trees

Inverse texture synthesis (ITS) plays an important role in many computer vision applications. It aims at generating small compaction images to capture significant features of textures, from which arbitrarily large images with similar textures can be re‐synthesised. This study presents a fast approach to ITS with two algorithms developed in hierarchical wavelet packet (WP) trees: the modified inverse texture synthesis (MITS) algorithm, which extends the ITS algorithm into the WP domain, and the wavelet‐packet‐tree‐based cropping (WPTC) algorithm for the initialisation of MITS. Experimental results show that the combination of WPTC and MITS termed the image compaction in wavelet packet trees algorithm outperforms the ITS algorithm in terms of the ‘peak signal‐to‐noise ratio’ and computation time.

Extracting Corresponding Point Based on Texture Synthesis for Nearly Flat Textureless Object Surface

Since the image feature points are always gathered at the range with significant intensity change, such as textured portions or edges of an image, which can be detected by the state-of-the-art intensity based point-detectors, there is nearly no point in the areas of low textured detected by classical interest-point detectors. In this paper we describe a novel algorithm based on affine transform and graph cut for interest point detecting and matching from wide baseline image pairs with weakly textured object. The detection and matching mechanism can be separated into three steps: firstly, the information on the large textureless areas will be enhanced by adding textures through the proposed texture synthesis algorithm TSIQ. Secondly, the initial interest-point set is detected by classical interest-point detectors. Finally, graph cuts are used to find the globally optimal set of matching points on stereo pairs. The efficacy of the proposed algorithm is verified by three kinds of experiments, that is, the influence of point detecting from synthetic texture with different texture sample, the stability under the different geometric transformations, and the performance to improve the quasi-dense matching algorithm, respectively.

Novel Synthesis Method for Image of Materials Texture

Most patch-based texture synthesis algorithms using Markov Random Field for composite materials only considers color similarity between the corresponding pixels. The traditional algorithms are lack of adaptability, so the size of patches needs to be defined artificially in advance as the result of blurring of image texture features for composite materials. In order to improve above problems, a new patch-based sampling algorithm for synthesizing textures from an input sample image texture of composite materials is presented in this paper. By using patches of the sample texture as building blocks for image texture synthesis of composite materials, this algorithm makes high-quality texture synthesis for a wide variety of textures ranging regular to stochastic. The method is effective by our experimental results.

An iterated randomized search algorithm for large-scale texture synthesis and manipulations

In this paper, we introduce a novel iterated random search method for large-scale texture synthesis and manipulations. Previous researches on texture synthesis and manipulation have reached a great achievement both on quality and performance. However, the cost of the popular exhaustive search-based methods is still high especially for large-scale and complex synthesis scenes. Our algorithm contributes great improvements on performances about 2---50 times over the typical patch-based synthesis methods. Texture patterns have been well-known formalized as a Markov Random Field (MRF) whose two hypotheses, stationarity and locality, drive our bold guess that a random sampling may just catch a good match and allows us to propagate the natural coherence in the neighborhood. Meanwhile, the iteration constantly updates the bad guesses to make our algorithm converge fast with the results in the state of the art. We also provide a simple theoretical analysis to compare our iterated randomized search model and the classical synthesis algorithms. Besides, this simple method turns out to work well in various applications as well, such as texture transfer, image completion and video synthesis.

Detection and Inpainting of Facial Wrinkles Using Texture Orientation Fields and Markov Random Field Modeling

Facial retouching is widely used in media and entertainment industry. Professional software usually require a minimum level of user expertise to achieve the desirable results. In this paper, we present an algorithm to detect facial wrinkles/imperfection. We believe that any such algorithm would be amenable to facial retouching applications. The detection of wrinkles/imperfections can allow these skin features to be processed differently than the surrounding skin without much user interaction. For detection, Gabor filter responses along with texture orientation field are used as image features. A bimodal Gaussian mixture model (GMM) represents distributions of Gabor features of normal skin versus skin imperfections. Then, a Markov random field model is used to incorporate the spatial relationships among neighboring pixels for their GMM distributions and texture orientations. An expectation-maximization algorithm then classifies skin versus skin wrinkles/imperfections. Once detected automatically, wrinkles/imperfections are removed completely instead of being blended or blurred. We propose an exemplar-based constrained texture synthesis algorithm to inpaint irregularly shaped gaps left by the removal of detected wrinkles/imperfections. We present results conducted on images downloaded from the Internet to show the efficacy of our algorithms.

Fullbore Image Construction of Imaging Logging Based on the Improved Texture Inpainting Method

The image inpainting method based on CriminiciA’s algorithm is slowly complete the image for large blank area. An improved algorithm based on the classic texture synthesis algorithm for image inpainting is proposed for imaging logging inpainting, which is used to generate the fullbore image. Two schemes, the local search method and priority calculation with TV model, are employed in the improved texture synthesis method. Some examples were given to demonstrate the effectiveness of the proposed algorithm on dealing with fullbore image construction with large blank area and raising efficiency obviously.

Maximum-likelihood based synthesis of volumetric textures from a 2D sample.

We propose a genuine 3D texture synthesis algorithm based on a probabilistic 2D Markov random field conceptualization, capable of capturing the visual characteristics of a texture into a unique statistical texture model. We intend to reproduce, in the volumetric texture, the interactions between pixels learned in an input 2D image. The learning is done by nonparametric Parzen-windowing. Optimization is handled voxel by a relaxation algorithm, aiming at maximizing the likelihood of each voxel in terms of its local conditional probability function. Variants are proposed regarding the relaxation algorithm and the heuristic strategies used for the simultaneous handling of the orthogonal slices containing the voxel. The procedures are materialized on various textures through a comparative study and a sensitivity analysis, highlighting the variants strengths and weaknesses. Finally, the probabilistic model is compared objectively with a nonparametric neighborhood-search-based algorithm.

A Texture Synthesis Method Based on Multi-resolution Matching

Texture synthesis is the field of computer graphics and related basic core issues. Studies have shown that the MRF model-based two-dimensional image texture synthesis algorithm, the synthesis results are directly affected by the magnitude of the impact of random images; that is consistent with a high degree of MRF model is better than other texture synthesis texture. The same time, the quality of synthetic images and synthesis algorithms is proportional to time-consuming. In this paper, the synthesis of the texture image decomposition strategy is introduced and the concept of multi-resolution atlas. It can be used to guide the texture partition, to improve the quality of texture synthesis. Experiments show that the proposed algorithm is effective.

Evaluating a Role for Oncotype Dx Breast Cancer Assay in the Management of Ductal Carcinoma In Situ

lumpectomy and adjuvant radiation at the Nova Scotia Cancer Center from July 2010 to December 2011. During breast conserving surgery, four surgical clips were placed on superior, inferior, lateral and medial walls of the lumpectomy cavity. Patients were imaged twice, first with CT for treatment planning and again between fractions 11 and 13 of the adjuvant radiation. To assess the effect of the clips on delineating using the same image data, in-house software was developed to digitally remove the clips from CT images using texture synthesis algorithm. Four radiation oncologists specializing in breast cancer treatment contoured the lumpectomy cavity volume, first with the clips digitally removed, and then several weeks later with the clips restored. Contours from three of the four participating radiation oncologists were included in the analysis, based on adherence to contouring guidelines. Contoured image sets were analyzed with regard to cavity volume, dimensions and concordance index. Statistical analysis was performed using a paired ttest. Results: The presence of clips significantly increased lumpectomy cavity volumes to 26.42 cc from 23.50 cc without clips (p < 0.0001). The presence of clips significantly increased the mean craniocaudal (CC), anteroposterior (AP) and lateral dimension by 7 mm, 2.3 mm, and 3 mm (all p < 0.01). Surgical clips improved consistency in delineation among observers in the craniocaudal dimension (p Z 0.005). Anteroposterior and lateral standard deviations were not affected significantly. There was also no significant difference in average concordance index with the presence of the surgical clips. Conclusions: The presence of surgical clips improves consistency of lumpectomy cavity delineation among radiation oncologists and also influences average delineated cavity volume and dimensions. Author Disclosure: S. Atrchian: None. P. Sadeghi: None. W. Cwajna: None. L. Helyer: None. D. Rheaume: None. M. Nolan: None. R. Rutledge: None. V. Calverley: None. S. Bennett: None. J. Robar: None.

Challenges in adapting example-based texture synthesis for panoramic map creation: a case study

Panoramic hiking and skiing maps are popular among tourists and map collectors. Such three-dimensional (3D) maps allow for easy orientation and provide the observer with an immersive impression of the landscape to be discovered or remembered. The most impressive panoramic masterpieces are almost exclusively painted manually or with minor digital tool support. Software packages that allow modern cartographers to create 3D maps of comparable visual quality (semi-) automatically are currently not available. Computer graphics has developed a number of methods for painterly rendering, including imitating the characteristics of a panorama artist's brush stroke and raster-based methods that synthesize new texture from examples. In this article, the latter approach is explored, and the idea of creating terrain textures for arbitrary regions by reassembling them from pieces of scanned hand-painted masterworks is pursued. Panorama painters vary the appearance of land cover depending on terrain characteristics and viewing parameters. This article suggests how the example-based texture synthesis approach could be adapted to accommodate such dependencies. A case study of transferring the appearance of H.C. Berann's hand-painted panorama of the Swiss Jungfrau region to a digital panorama of a different region is presented. The case study shows that a number of previously unanticipated hurdles are encountered when using hand-painted panoramas as input to an example-based texture synthesis algorithm. By identifying the challenges of applying texture-by-example to panoramic map making and by suggesting possible solutions, the authors aim to promote the creation of more visually appealing and legible digital panoramic maps.

Novel Methods for Non Uniform Patch Based Texture Synthesis Using Random Selection of Patches

Two simple image based methods of generating novel visual appearance in the synthesized texture are presented in the present paper. The synthesized output texture contains square patches of non uniform sizes. Two categories of non uniform patch based texture synthesis namely; row-wise patch based texture synthesis and quadrant-wise patch based texture synthesis are discussed. In both the cases the procedure ends when the output texture is completely synthesized. These texture synthesis algorithms are fast and very simple for patches of non-uniform sizes and they produce surprisingly good results for a wide range of textures. The results obtained using the proposed method is encouraging and reasonable in some cases.