Controlling strokes in fast neural style transfer using content transforms

Reimann, Max; Buchheim, Benito; Semmo, Amir; Döllner, Jürgen; Trapp, Matthias

doi:10.1007/s00371-022-02518-x

Cited by 10 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate our excellent performance, we compared out method with several state-of-the-art methods, including WCT2 [36], AdaIN [37], Johnson [16], StyTr2 [9], Style-TUNE [38] and Gatys [1]. As shown in Figure 3, it is observed that our method improves the quality of style-transferred images significantly.…”

Section: Visual Comparisonmentioning

confidence: 94%

A Compositional Transformer Based Autoencoder for Image Style Transfer

Feng

Zhang

et al. 2023

Electronics

View full text Add to dashboard Cite

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.

show abstract

Section: Visual Comparisonmentioning

confidence: 94%

A Compositional Transformer Based Autoencoder for Image Style Transfer

Feng

Zhang

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…It can simultaneously control stroke intensity and size. The experimental results showed that the model make users achieving resolutions exceeding 20 million pixels and good output fidelity [11]. Hollandi et al developed a deep learning-based cell nucleus segmentation framework that utilizes image style transfer to automatically generate cell nucleus segmentation masks.…”

Section: Jing Et Al Proposed a New Normalization Module Calledmentioning

confidence: 99%

Intelligent Design of Ethnic Patterns in Clothing using Improved DCGAN for Real-Time Style Transfer

Liu,

2023

IJACSA

View full text Add to dashboard Cite

In view of the problems that traditional real-time style transmission technology requires a large number of sample map training, low image quality, lack of realism and detail, this study combines the improved generative adversarial network (GANs) with real-time style transfer technology, and enhances the real-time style transfer calculation with adaptive instance normalization. As a result, a novel intelligent clothing ethnic pattern design model is developed. Experimental results show that the model reduces physical memory usage by 45.7%, with only 453MB, and utilizes only 26% of CPU resources in terms of CPU usage. The training time is approximately 20 minutes and 48 seconds. This model performance is obviously higher than other models. The designed intelligent clothing ethnic pattern design model in this study demonstrates higher clarity and shorter processing time, and has potential applications in the field of image generation.

show abstract

“…From the initial single-model single-style algorithm to single-model multi-style algorithm, subsequently, 2 – 14 a large number of CNN-based arbitrary style image migration methods have been proposed, and this technological breakthrough has made style migration more flexible and practical. To enhance the style expression, some of them start from the brushstroke, 15 – 17 which generates meaningful stroke parameters in the vectorized environment, which are used to control the stroke size as well as the intensity, and further render the texture to present the unique brushstroke characteristics of the artist. However, obtaining many artists’ brushstrokes is not easy.…”

Section: Introductionmentioning

confidence: 99%

MA-GAN: the style transfer model based on multi-adaptive generative adversarial networks

Zhao,

Qian,

Song

2024

J. Electron. Imag.

View full text Add to dashboard Cite

Existing style transfer methods need more texture structure of style images with aesthetic guidance, resulting in the loss of a large amount of texture details, which affects the visual effect. We propose a style transfer model based on multi-adaptive generative adversarial networks (MA-GANs) to address this. Specifically, the aesthetic ability learned by the discriminator is used for feature extraction, and the obtained more generalized features are passed into the multi-attention aesthetic module, which includes a collaborative self-attention (CSA) module and a self-attention normalization (SAN) module. The CSA calculates the correlation between the entangled style features and aesthetic features, capturing texture details and style geometric structures. The SAN balances the content semantic structure with the style geometric structure, harmoniously integrating the style pattern into the content image, thus achieving a more practical style transfer. Extensive qualitative and quantitative experimental studies demonstrate the superiority of MA-GAN in visual quality, enabling the synthesis of art images with smooth brushstrokes and rich colors.

show abstract

Controlling strokes in fast neural style transfer using content transforms

Cited by 10 publications

References 41 publications

A Compositional Transformer Based Autoencoder for Image Style Transfer

A Compositional Transformer Based Autoencoder for Image Style Transfer

Intelligent Design of Ethnic Patterns in Clothing using Improved DCGAN for Real-Time Style Transfer

MA-GAN: the style transfer model based on multi-adaptive generative adversarial networks

Contact Info

Product

Resources

About