Controllable Artistic Text Style Transfer via Shape-Matching GAN

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 .

Stylized image denoising via noise style transfer and Quasi Siamese network

We introduce a simple method for text style transfer that frames style transfer as denoising: we synthesize a noisy corpus and treat the source style as a noisy version of the target style. To control for aspects such as preserving meaning while modifying style, we propose a reranking approach in the data synthesis phase. We evaluate our method on three novel style transfer tasks: transferring between British and American varieties, text genres (formal vs. casual), and lyrics from different musical genres. By measuring style transfer quality, meaning preservation, and the fluency of generated outputs, we demonstrate that our method is able both to produce high-quality output while maintaining the flexibility to suggest syntactically rich stylistic edits.

With the rapid development of computer computing power, as an important method in the field of artificial intelligence, deep learning has amazing learning ability, especially in dealing with massive data, which makes deep learning in the fields of image recognition, image classification, natural language processing, data mining and unmanned driving, Has shown an extraordinary role. In previous studies, the style transfer algorithm has not developed well due to the poor computing power of Computer, the basic configuration of computer hardware can not meet the minimum requirements and the poor image effect after migration. However, with the development of computer hardware and the rapid change of GPU computing power, the style transfer network based on deep learning has become a hot issue in the study of style transfer in recent years. According to the research, although the traditional style transfer method can obtain the texture, color and other information of the style image, the model needs to be learned every time a new target image is generated, and the time cost during this period is very high. In this way, the trained model is not repeatable, and the generated image is often very random and can not get good results. Therefore, the emergence of style transfer methods based on deep learning solves the limitations of traditional style transfer methods. Style transfer methods based on deep learning are faster than traditional style transfer methods, and the generalization of the model is better. The style transfer algorithms of main neural networks are divided into two categories, Slow style transfer based on image iteration and fast style transfer based on model iteration. VGG network model can combine style image and content image, and greatly improve the style transfer efficiency of image.

Text style transfer (TST) without parallel data has achieved some practical success. However, most of the existing unsupervised text style transfer methods suffer from (i) requiring massive amounts of non-parallel data to guide transferring different text styles. (ii) colossal performance degradation when fine-tuning the model in new domains. In this work, we propose DAML-ATM (Domain Adaptive Meta-Learning with Adversarial Transfer Model), which consists of two parts: DAML and ATM. DAML is a domain adaptive meta-learning approach to learning general knowledge in multiple heterogeneous source domains, capable of adapting to new unseen domains with a small amount of data. Moreover, we propose a new unsupervised TST approach Adversarial Transfer Model (ATM), composed of a sequence-to-sequence pre-trained language model and uses adversarial style training for better content preservation and style transfer. Results on multi-domain datasets demonstrate that our approach generalizes well on unseen low-resource domains, achieving state-of-the-art results against ten strong baselines.

Seismic data are widely used in oil, gas, and other kinds of mineral exploration and development. However, due to low artificial interpretation accuracy and small sample sizes, seismic data may not meet the needs of convolutional neural network training. There are major differences between optical image and seismic data, making it difficult for a model to learn seismic data characteristics. Therefore, a style transfer network is necessary to make the styles of optical image and seismic data more similar. Since the stylization effect of a seismic section is similar to that of most art styles, based on an in-depth study of image style transfer, this paper compared the effects of various style transfer models, and selected a Laplacian pyramid network to carry out a study of seismic section stylization. It transmits low-resolution global style patterns through a drafting network, revises high-resolution local details through correction networks, and aggregates all pyramid layers to output final stylized images of seismic profiles. Experiments show that this method can effectively convey the whole style pattern without losing the original image content. This style transfer method, based on the Laplacian pyramid network, provides theoretical guidance for the fast and objective application of the model to seismic data features.

To improve the expressiveness and realism of illustration images, the experiment innovatively combines the attention mechanism with the cycle consistency adversarial network and proposes an efficient style transfer method for illustration images. The model comprehensively utilizes the image restoration and style transfer capabilities of the attention mechanism and the cycle consistency adversarial network, and introduces an improved attention module, which can adaptively highlight the key visual elements in the illustration, thereby maintaining artistic integrity during the style transfer process. Through a series of quantitative and qualitative experiments, high-quality style transfer is achieved, especially while retaining the original features of the illustration. The results show that when running on the Monet2photo dataset, when the system iterates to 72 times, the loss function value of the research method approaches the target value of 0.00. On the Horse2zebra dataset, as the sample size increases, the research method has the smallest FID value, and the value approaches 40.00 infinitely. With the change of peak signal-to-noise ratio, the accuracy of the research algorithm has been greater than 95.00%. Practical application found that the color of the image obtained by the research method is more gorgeous and the line features are more obvious. The above results all show that the research method has achieved more satisfactory results in the task of style transfer of illustration images, especially in terms of the accuracy of style transfer and the retention of image details.

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.

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.

Neural style transfer (NST) is a deep learning technique that produces an unprecedentedly rich style transfer from a style image to a content image. It is particularly impressive when it comes to transferring style from a painting to an image. NST was originally achieved by solving an optimization problem to match the global statistics of the style image while preserving the local geometric features of the content image. The two main drawbacks of this original approach is that it is computationally expensive and that the resolution of the output images is limited by high GPU memory requirements. Many solutions have been proposed to both accelerate NST and produce images with larger size. However, our investigation shows that these accelerated methods all compromise the quality of the produced images in the context of painting style transfer. Indeed, transferring the style of a painting is a complex task involving features at different scales, from the color palette and compositional style to the fine brushstrokes and texture of the canvas. This paper provides a solution to solve the original global optimization for ultra‐high resolution (UHR) images, enabling multiscale NST at unprecedented image sizes. This is achieved by spatially localizing the computation of each forward and backward passes through the VGG network. Extensive qualitative and quantitative comparisons, as well as a perceptual study, show that our method produces style transfer of unmatched quality for such high‐resolution painting styles. By a careful comparison, we show that state‐of‐the‐art fast methods are still prone to artifacts, thus suggesting that fast painting style transfer remains an open problem.

Style transfer has received much attention, and Chinese character style transfer is an important application. In the previous Chinese character style transfer methods, most of the methods separately establish a mapping from source font to target Chinese character for each specific target font. It is impossible to extend a single model to other styles. The model training is based on the amount of Chinese character data from a single font, and the demand of the character is greater. In fact, different font style transfer tasks have certain commonalities. Therefore, we use multiple fonts in the data set and combine these fonts into multiple sets of Chinese character style transfer tasks. These tasks will be trained at the same time, instead of that only one font style transfer task training is achieved at a time like the previous work. In order to achieve the purpose of extracting and fusing the content features and style feature, we propose a style transfer network composed of content encoder, style encoder, feature fusion module, and decoder, based on the fusion of multi-scale content and style features. Through the experimental results, it can be found that, using our method, training the style transfer of multiple fonts at the same time can help any one of them to generate better results with only a few samples.

Neural style transfer represented a paradigm shift in image artistic rendering and applications in digital entertainment. Generative adversarial networks are considered as a general solution for style transfer problems. Researchers have explored multiple learning algorithms to increase the learning ability of style transfer networks. However, such research has overlooked an important outside motivator: social preference. Classical style transfer networks are trained offline and worked as a stationary model to transfer photos into stylized images, without any interaction with the environment. Based on the ideas from online training, we propose a new coarse-to-fine training strategy for neural style transfer systems to adapt to social preference change. In coarse stage, a primary model is learned via normal training method. In fine stage, the model is updated with online learning approach and sequentially added new data. We show that our approach exhibits improved performance compared to stationary model from visual effect and reflection of social preference. We conclude that the coarse-to-fine training strategy can improve the output of the generative model in social media environment.

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.

The style transfer task (here style is used in a broad “authorial” sense with many aspects including register, sentence structure, and vocabulary choice) takes text input and rewrites it in a specified target style preserving the meaning, but altering the style of the source text to match that of the target. Much of the existing research on this task depends on the use of parallel datasets. In this work we employ recent results in unsupervised cross-lingual language modeling (XLM) and machine translation to effect style transfer while treating the input data as unaligned. First, we show that adding “content embeddings” to the XLM which capture human-specified groupings of subject matter can improve performance over the baseline model. Evaluation of style transfer has often relied on metrics designed for machine translation which have received criticism of their suitability for this task. As a second contribution, we propose the use of a suite of classical stylometrics as a useful complement for evaluation. We select a few such measures and include these in the analysis of our results.

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.