Hepatic Texture Synthesis Method Based on the Accelerated CUDA

An improved image texture synthesis based on algorithm convolution neural network

Texture Mapping plays a very important role in Computer Graphics. Texture Synthesis is one of the main methods to obtain textures, it makes use of sample textures to generate new textures. Texture Transfer is based on Texture Synthesis, it renders objects with textures taken from different objects. Currently, most of Texture Synthesis and Transfer methods use a single sample texture. A method for Texture Synthesis adn Transfer from multi samples was presented. For texture synthesis, the L-shaped neighborhood seaching approach was used. Users specify the proportion of each sample, the number of seed points, and these seed points are scattered randomly according to their samples in horizontal and vertical direction synchronously to synthesize textures. The synthesized textures are very good. For texture transfer, the luminance of the target image and the sample textures are analyzed. This procedure is from coarse to fine, and can produce a visually pleasing result.

Computer graphics applications often use textures to decorate virtual objects without modeling geometric details. These textures can be seamlessly generated from sample textures using texture synthesis algorithms. However, most existing texture synthesis algorithms are designed for rectangular domains and cannot be easily extended to general surfaces. In this paper, we present a novel method for texture synthesis and texture growing on triangle mesh with arbitrary topology. Using the sampled texture patches as the building blocks for texture synthesis, the visually seamless texture can be synthesized for a wide variety of textures ranging from regular to stochastic. The synthesizing process generates an initial texture block from the input texture patches and then iteratively searches for all texture blocks from the sampled texture patches to select a patch which optimizes the smoothness of the overlapping boundaries of the synthesized texture. It is showed that the proposed scheme is effective and efficient for synthesizing and growing of a wide range of textures on surfaces.

Sample based texture synthesis allows the generation of arbitrarily sized textures based on a small sample image. One main drawback of the technique is that a new pixel or patch is selected only considering local information in the generated texture. Thus structural error can't assure to be avoided for structural textures. To accelerate texture synthesis process and to avoid structural mismatch in the output picture, we present in this paper a structural pattern analysis (SPA) algorithm and a texture synthesis method using the algorithm. The pattern analysis tool also quantizes the texture randomness in macro scope view. It can be used in other applications such as automatic texture classification and quality evaluation of synthesized texture. We illustrate our result with some examples.

Texture synthesis technology can not only be used for texture transmission and repair damaged photos, but also has a broad application prospect in large-scale virtual scene rendering. In order to solve the problems of seam aliasing in texture mapping and considering the self-similarity of texture, this paper defines the trend function based on the biased random walk algorithm, divides the motion unit with different seed points and constructs the adjacency matrix, and calculates by matching labels Random walk stepping probability to realize texture synthesis. Compared with the background image segmentation results, it can be seen that the texture image generated by the algorithm in this paper presents similarity and continuity visually, and shows strong randomness at the same time.

Texture synthesis is the hot research topic in the field of computer vision, computer graphics and image processing. Sample-based texture synthesis method has been proposed and becomes a new texture tiling technique with the development of the texture mapping and procedural texture synthesis. Image Quilting stitching algorithm is an ideal algorithm for the texture stitching. In this article, by using the image Quilting algorithm to finish the texture transfer and stitch the objective texture image, whose texture style does not exist in the initial image. In experiments, by transferring the style of the human face image and character image respectively, verified the effectiveness of this proposed algorithm.

Texture synthesis has been an active research area in computer graphics, vision, and image processing. A hybrid texture synthesis approach that combines the strength of Ashikhmin’s [1] and Liang’s [11] algorithms is presented in this paper. Using patches from the input sample texture to extend the input itself, more suitable valid candidate pixels in the input sample can be more precisely determined. An extra original position array is used to record the valid pixel position in the extended region of input sample texture such that the candidate pixel can be retrieved efficiently. Pasting patches with more global information of texture features to initialize the output texture, the texture synthesis process tends to grow larger pieces in the output texture so that the perceptual similarity is reserved as much as possible. Many classes of textures have been used to test our approach. As the experimental results showed, the proposed hybrid approach effectively and efficiently synthesizes high-quality textures from a wide variety of textures.

We present an efficient multiresolution block sampling-based texture synthesis algorithm that works well for a wide variety of challenging textures. We consider the texture synthesis as a procedure that first estimates and then resamples a probability function. To achieve the effect of good and fast estimation of the probability function for a given texture as well as to retain the structural information during synthesis, we propose a concept of block sampling and a corresponding novel scheme of texture synthesis based on multiresolution block sampling (MBS). The computational complexity of the proposed algorithm is much lower than that of existing algorithms. Experimental results have shown that his novel texture synthesis algorithm produces superior results for many challenging textures.

We propose a layered image inpainting scheme based on image decomposition. The damaged image is first decomposed into three layers: cartoon, edge, and texture. The cartoon and edge layers are repaired using an adaptive offset operator that can fill-in damaged image blocks while preserving sharpness of edges. The missing information in the texture layer is generated with a texture synthesis method. By using discrete cosine transform (DCT) in image decomposition and trading between resolution and computation complexity in texture synthesis, the processing time is kept at a reasonable level.

Texture synthesis is a fundamental problem in computer graphics that would benefit various applications. Existing methods are effective in handling 2D image textures. In contrast, many real-world textures contain meso-structure in the 3D geometry space, such as grass, leaves, and fabrics, which cannot be effectively modeled using only 2D image textures. We propose a novel texture synthesis method with Neural Radiance Fields (NeRF) to capture and synthesize textures from given multi-view images. In the proposed NeRF texture representation, a scene with fine geometric details is disentangled into the meso-structure textures and the underlying base shape. This allows textures with meso-structure to be effectively learned as latent features situated on the base shape, which are fed into a NeRF decoder trained simultaneously to represent the rich view-dependent appearance. Using this implicit representation, we can synthesize NeRF-based textures through patch matching of latent features. However, inconsistencies between the metrics of the reconstructed content space and the latent feature space may compromise the synthesis quality. To enhance matching performance, we further regularize the distribution of latent features by incorporating a clustering constraint. In addition to generating NeRF textures over a planar domain, our method can also synthesize NeRF textures over curved surfaces, which are practically useful. Experimental results and evaluations demonstrate the effectiveness of our approach.

An image inpainting technique is proposed to improve quality of photographs taken under poor weather conditions. Pale and gloomy sky is first replaced with more pleasant looking blue sky and white clouds. Transition regions near complicated boundaries are modified using a texture synthesis method that makes the sky and ground objects grow towards each other along normal directions obtained from the general trend of the boundary. This produces retouched pictures with a natural appearance

Many natural and man-made surface patterns are created by interactions between texture elements and surface geometry. We believe that the best way to create such patterns is to synthesize a texture directly on the surface of the model. Given a texture sample in the form of an image, we create a similar texture over an irregular mesh hierarchy that has been placed on a given surface.Our method draws upon texture synthesis methods that use image pyramids, and we use a mesh hierarchy to serve in place of such pyramids. First, we create a hierarchy of points from low to high density over a given surface, and we connect these points to form a hierarchy of meshes. Next, the user specifies a vector field over the surface that indicates the orientation of the texture. The mesh vertices on the surface are then sorted in such a way that visiting the points in order will follow the vector field and will sweep across the surface from one end to the other. Each point is then visited in turn to determine its color. The color of a particular point is found by examining the color of neighboring points and finding the best match to a similar pixel neighborhood in the given texture sample. The color assignment is done in a coarse-to-fine manner using the mesh hierarchy. A texture created this way fits the surface naturally and seamlessly.

This paper proposes Markovian Generative Adversarial Networks (MGANs), a method for training generative neural networks for efficient texture synthesis. While deep neural network approaches have recently demonstrated remarkable results in terms of synthesis quality, they still come at considerable computational costs (minutes of run-time for low-res images). Our paper addresses this efficiency issue. Instead of a numerical deconvolution in previous work, we precompute a feed-forward, strided convolutional network that captures the feature statistics of Markovian patches and is able to directly generate outputs of arbitrary dimensions. Such network can directly decode brown noise to realistic texture, or photos to artistic paintings. With adversarial training, we obtain quality comparable to recent neural texture synthesis methods. As no optimization is required any longer at generation time, our run-time performance (0.25M pixel images at 25Hz) surpasses previous neural texture synthesizers by a significant margin (at least 500 times faster). We apply this idea to texture synthesis, style transfer, and video stylization.

This paper presents an example based non-photorealistic image rendering algorithm, which employs patch-based texture synthesis approaches, as well as speeds up the texture synthesis process by exploiting particle swarm optimization during the matching search process. This algorithm also accomplishes orientation control of matching patches in structure and details through appropriate parameter setting. Once a certain sample image with artistic style is presented, the algorithm can accomplish image analogy by transferring the style to the target.

We investigate semi‐stochastic tilings based on Wang or corner tiles for the real‐time synthesis of example‐based textures. In particular, we propose two new tiling approaches: (1) to replace stochastic tilings with pseudo‐random tilings based on the Halton low‐discrepancy sequence, and (2) to allow the controllable generation of tilings based on a user‐provided probability distribution. Our first method prevents local repetition of texture content as common with stochastic approaches and yields better results with smaller sets of utilized tiles. Our second method allows to directly influence the synthesis result which—in combination with an enhanced tile construction method that merges multiple source textures—extends synthesis tasks to globally‐varying textures. We show that both methods can be implemented very efficiently in connection with tile‐based texture mapping and also present a general rule that allows to significantly reduce resulting tile sets.