Object Texture Transform Based on Improved CycleGAN

This work presents Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style representation learning and transfer framework, that can fit in most existing arbitrary image style transfer models, such as CNN-based, ViT-based, and flow-based methods. As the key component in image style transfer tasks, a suitable style representation is essential to achieve satisfactory results. Existing approaches based on deep neural networks typically use second-order statistics to generate the output. However, these hand-crafted features computed from a single image cannot leverage style information sufficiently, which leads to artifacts such as local distortions and style inconsistency. To address these issues, we learn style representation directly from a large number of images based on contrastive learning by considering the relationships between specific styles and the holistic style distribution. Specifically, we present an adaptive contrastive learning scheme for style transfer by introducing an input-dependent temperature. Our framework consists of three key components: a parallel contrastive learning scheme for style representation and transfer, a domain enhancement (DE) module for effective learning of style distribution, and a generative network for style transfer. Qualitative and quantitative evaluations show the results of our approach are superior to those obtained via state-of-the-art methods. The code is available at https://github.com/zyxElsa/CAST_pytorch .

With the rapid development of deep learning technology, style transfer has achieved significant breakthroughs at both algorithmic and application levels, greatly promoting innovative interactions between content and style. This paper comprehensively reviews the fundamental concepts, classifications, and widespread applications of style transfer within neural networks, with a particular focus on the principles, diverse variants, and synthesis techniques of neural network-based style transfer. Additionally, the article explores image style transfer as a research hotspot in the field of artificial intelligence and computer vision, highlighting that traditional methods primarily rely on physical and texture synthesis techniques, which often result in coarse outcomes and poor robustness. Through comparative analysis, this paper outlines the development trajectory and latest research advances in image style transfer and proposes future research directions.

Style transfer refers to extracting styles from a specified style image template, and mapping the extracted style features to the content image without destroying the image content. At present, the use of deep learning methods for style transfer is one of the hotspots in the field of image research. This paper implements an image style transfer architecture based on cyclic consistent generative adversarial network, i. e., cyclic consistent confrontation network, and uses densely connected convolutional network to deepen the number of network layers. Test results show that stylized image with the proposed method is more obvious than that of the original cyclic consistent generative adversarial network, and the image quality is improved apparently.

The rapid development of artificial intelligence technology and deep learning technology has also promoted the popularization and application of image style transfer in all walks of life. In the traditional ceramic industry, the application of image style transfer technology is still rare. This article is based on the style transfer training of ceramic blue and white images and uses three methods of rapid style transfer, direct style transfer and image pre-processing style transfer to conduct experiments. According to the results of image quality evaluation, it is concluded that the method suitable for the style transfer of ceramic blue and white images is the image pre-processing style transfer method.

Style transfer means that the characteristic information of the style image is transferred to the content image under a given content and style picture. Meanwhile, the transferred image is faithful to the content image. Currently, the transferred image has many problems such as artifacts and distortion of the spatial structure. To solve these problems, a dynamic residual-multi-level and multi-pooling network combined with our improved style transfer algorithm is proposed in this paper to achieve better effect of arbitrary image style transfer. To elaborate more specifically, First of all, We add a dynamic-residual network layer to the network to speed up the training speed of the network model and improve the robustness of the network. Secondly, we use a multi-level and multi-pooling layer to extract more specific spatial structure, edge texture and other information in the image, and the network layer also has an additional denoising effect. Third, the improved style transfer algorithm aligns the mean and variance of the content and style images from a statistical point of view, and realizes adaptive arbitrary style transfer of the original input image features. Finally, during model training, the convergence speed of the proposed approach is faster than other current advanced methods, and the transferred renderings are better than other network models in quantitative comparisons such as SSIM and Gram. It is worth mentioning that our model has the fastest real-time transfer speed and can realize any image style transfer.

A popular project in computer vision in recent years is called "image transfer", which attempts to create new images containing features from abstract properties of the content and style of a given image. Convolutional neural networks have generated the basic components of image style transfer, significantly improving transfer accuracy and visualization effect, thanks to deep learning's quick progress. The purpose of this study is to highlight the most recent developments in the area of deep learning-based picture style transfer. We first provide a detailed introduction to the traditional style transfer algorithms from the frameworks of generative adversarial networks and convolutional neural networks., including the design ideas research issues, key steps, advantages and disadvantages. On a few application tasks, we qualitatively compare the visualization outcomes of various approaches, and we talk about the subject's current issues and potential future developments.

In many fields, image style transfer has been a popular topic. It also has a long history; the earliest examples date back to the previous century. A number of style transfer techniques are currently flourishing, from manual modeling to the use of neural networks. Image style transfer methods is improving and taking less time. This paper is separated into two main categories to analyze based on picture iteration and model iteration - and summarizes the various techniques of image style transfer based on deep learning in accordance with the timeline. This paper introduces maximum mean difference, Markov random field, and deep image analogy in picture iteration-based image style transfer. In terms of model iteration-based image style migration, this paper introduces generative models and image reconstruction decoders. Finally, the paper presents some recommendations and outlook on the future.

To provide semantic image style transfer results which are consistent with human perception, transferring styles of semantic regions of the style image to their corresponding semantic regions of the content image is necessary. However, when the object categories between the content and style images are not the same, it is difficult to match semantic regions between two images for semantic image style transfer. To solve the semantic matching problem and guide the semantic image style transfer based on matched regions, we propose a novel semantic context-aware image style transfer method by performing semantic context matching followed by a hierarchical local-to-global network architecture. The semantic context matching aims to obtain the corresponding regions between the content and style images by using context correlations of different object categories. Based on the matching results, we retrieve semantic context pairs where each pair is composed of two semantically matched regions from the content and style images. To achieve semantic context-aware style transfer, a hierarchical local-to-global network architecture, which contains two sub-networks including the local context network and the global context network, is proposed. The former focuses on style transfer for each semantic context pair from the style image to the content image, and generates a local style transfer image storing the detailed style feature representations for corresponding semantic regions. The latter aims to derive the stylized image by considering the content, the style, and the intermediate local style transfer images, so that inconsistency between different corresponding semantic regions can be addressed and solved. The experimental results show that the stylized results using our method are more consistent with human perception compared with the state-of-the-art methods.

In this work, we focus on building style transfer, which transforms ruin or old buildings to modern architecture. Inspired by Gaty's and Goodfellow's style transfer and generative adversarial network (GAN), we use CycleGAN to conquer this type of problem. As we know, image style transfer usually generated unexpected artifacts. To avoid the artifacts and generate better images, we add so called “perception loss” into the network, which is the feature loss extracted by VGG pre-trained model. In the part of “cycle” structure, we adjust cycle loss by changing the ratio of weighting parameters. Finally, we collect images of both ruin (or old) and modern architecture from websites and use unsupervised learning to train the model. The experimental results show our proposed method indeed realize the modern architecture style transfer for ruin or old buildings.

Image style transfer has become a key technique in modern photo-editing applications. Although significant progress has been made to blend content from one image with style from another image, the synthesized image may have a hallucinatory effect when the texture from the style image is rich when processing high-resolution image style transfer tasks. In this paper, we propose a novel attention mechanism, named compositional attention, to design a compositional transformer-based autoencoder (CTA) to solve this above-mentioned issue. With the support from this module, our model is capable of generating high-quality images when transferring from texture-riched style images to content images with semantics. Additionally, we embed region-based consistency terms in our loss function for ensuring internal structure semantic preservation in our synthesized image. Moreover, information theory-based CTA is discussed and Kullback–Leibler divergence loss is introduced to preserve more brightness information for photo-realistic style transfer. Extensive experimental results based on three benchmark datasets, namely Churches, Flickr Landscapes, and Flickr Faces HQ, confirmed excellent performance when compared to several state-of-the-art methods. Based on a user study assessment, the majority number of users, ranging from 61% to 66%, gave high scores on the transfer effects of our method compared to 9% users who supported the second best method. Further, for the questions of realism and style transfer quality, we achieved the best score, i.e., an average of 4.5 out of 5 compared to other style transfer methods.

Image style transfer is a hot issue in the field of computer vision. It refers to the process that an image (content image) has a specified artistic style (style image) through the algorithm, which has an important application value. The complex spatial structure in the process of style transfer will make the details blurred and the local structure of the image distorted. In this paper, a new feature detection network is introduced for feature extraction of style content and style content, which has fewer simple parameters. In the transformation network, the adaptive Instance standardization layer is added after the convolution layer to improve the retention ability of the spatial structure of the content image. Large convolution kernels are replaced to reduce the number of model parameters while maintaining the same receptive field. The network model built in this paper can realize the rapid migration of various styles, strengthen the structural characteristics of images, and improve the detail effect of stylized images significantly.

The paper proposes a solution to effectively handle salient regions for style transfer between unpaired datasets. Recently, Generative Adversarial Networks (GAN) have demonstrated their potentials of translating images from source domain X to target domain Y in the absence of paired examples. However, such a translation cannot guarantee to generate high perceptual quality results. Existing style transfer methods work well with relatively uniform content, they often fail to capture geometric or structural patterns that always belong to salient regions. Detail losses in structured regions and undesired artifacts in smooth regions are unavoidable even if each individual region is correctly transferred into the target style. In this paper, we propose SDP-GAN, a GAN-based network for solving such problems while generating enjoyable style transfer results. We introduce a saliency network, which is trained with the generator simultaneously. The saliency network has two functions: (1) providing constraints for content loss to increase punishment for salient regions, and (2) supplying saliency features to generator to produce coherent results. Moreover, two novel losses are proposed to optimize the generator and saliency networks. The proposed method preserves the details on important salient regions and improves the total image perceptual quality. Qualitative and quantitative comparisons against several leading prior methods demonstrates the superiority of our method.

Image style transfer refers to the transformation of the style of image, so that the image details are retained to the maximum extent while the style is transferred. Aiming at the problem of low clarity of style transfer images generated by CycleGAN network, this paper improves the CycleGAN network. In this paper, the network model of auto-encoder and variational auto-encoder is added to the structure. The encoding part of the auto-encoder is used to extract image content features, and the variational auto-encoder is used to extract style features. At the same time, the generating network of the model in this paper uses first to adjust the image size and then perform the convolution operation to replace the traditional deconvolution operation. The discriminating network uses a multi-scale discriminator to force the samples generated by the generating network to be more realistic and approximate the target image, so as to improve the effect of image style transfer.

In recent years, arbitrary image style transfer has attracted more and more attention. Given a pair of content and style images, a stylized one is hoped that retains the content from the former while catching style patterns from the latter. However, it is difficult to simultaneously keep well the trade-off between the content details and the style features. To stylize the image with sufficient style patterns, the content details may be damaged, and sometimes the objects of images can not be distinguished clearly. For this reason, we present a new transformer-based method named STT (Style Transfer via Transformers) for image style transfer, and an edge loss function that can enhance the content details and avoid generating blurred results due to the excessive rendering of style features. Extensive qualitative and quantitative experiments demonstrate that STT achieves comparable performance to state-of-the-art image style transfer approaches while alleviating the content leak problem.

Image style transfer aims to change a picture’s style while maintaining the integrity of the image’s original information. Image style transfer techniques based on deep learning have expanded in variety as a result of the quick advancement of artificial intelligence technology, and have made breakthroughs in both transfer accuracy and visualization effect. Focusing on image style transfer based on depth learning, this paper systematically introduces its latest research progress. Specifically, according to the difference of network structure, this paper introduces four representative style transfer methods based on CNN and GAN, including their design ideas, process based, advantages and disadvantages. In addition, this paper also qualitatively and quantitatively compares the transfer results of different algorithms on different datasets. For GAN based method, AnimeGAN has a good conversion effect in style conversion. For the CNN based method, the combination of perceptual loss and feedforward network using perceptual loss is more prominent. Finally, this paper reviews the development and breakthrough of neural network style, and sorts out and discusses the differences and shortcomings of these technologies as well as some unresolved problems.