Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields

Jing, Yongcheng; Liu, Yang; Yang, Yezhou; Feng, Zunlei; Yu, Yizhou; Tao, Dacheng; Song, Mingli

doi:10.1007/978-3-030-01261-8_15

Cited by 101 publications

(113 citation statements)

References 35 publications

Supporting

Mentioning

113

Contrasting

Order By: Relevance

“…Methods such as [8,23] are dedicated to learn stroke control in transfer process. Jing et al [8] first proposes to achieve continuous stroke size control by incorporating multiple stroke sizes into one single StrokePyramid model. The StrokePyramid result shown in Figure 1 is produced by mixing two different stroke sizes.…”

Section: Introductionmentioning

confidence: 99%

Attention-Aware Multi-Stroke Style Transfer

Yao

Ren

Xie

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

164

126

View full text Add to dashboard Cite

Neural style transfer has drawn considerable attention from both academic and industrial field. Although visual effect and efficiency have been significantly improved, existing methods are unable to coordinate spatial distribution of visual attention between the content image and stylized image, or render diverse level of detail via different brush strokes. In this paper, we tackle these limitations by developing an attention-aware multi-stroke style transfer model. We first propose to assemble self-attention mechanism into a style-agnostic reconstruction autoencoder framework, from which the attention map of a content image can be derived. By performing multi-scale style swap on content features and style features, we produce multiple feature maps reflecting different stroke patterns. A flexible fusion strategy is further presented to incorporate the salient characteristics from the attention map, which allows integrating multiple stroke patterns into different spatial regions of the output image harmoniously. We demonstrate the effectiveness of our method, as well as generate comparable stylized images with multiple stroke patterns against the state-of-theart methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Attention-Aware Multi-Stroke Style Transfer

Yao

Ren

Xie

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

164

126

View full text Add to dashboard Cite

show abstract

“…To quantitatively evaluate the performance of the compared methods, we conducted a user study on the Amazon Mechanical Turk platform where observers were given im- [17] with stroke size evenly increasing from 256 to 768; (b) UT-Effect [31] with resolution level evenly increasing from 1 to 7; (c) the proposed method with evenly increasing from 0 to 1. All results are produced by one single model for each method.…”

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

“…2(d)), e.g., size or spatial frequency. Jing et al [17] proposed a stroke-controllable neural style transfer network (SC-NST) with adaptive receptive fields for stroke size control. Our work explores the glyph deformation degree ( Fig.…”

Section: Related Workmentioning

confidence: 99%

Controllable Artistic Text Style Transfer via Shape-Matching GAN

Yang

Wang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

109

View full text Add to dashboard Cite

b) adjustable stylistic degree of glyph (c) stylized text (d) application (e) liquid artistic text rendering (f) smoke artistic text rendering Figure 1: We propose a novel style transfer framework for rendering artistic text from a source style image in a scale-controllable manner.Our framework allows users to (b) adjust the stylistic degree of the glyph (i.e. deformation degree) in a continuous and real-time way, and therefore to (c) select the artistic text that is most ideal for both legibility and style consistency. The generated diverse artistic text will facilitate users to design (d) exquisite posters and (e)(f) dynamic typography. Embedded animation best viewed in Acrobat Reader. AbstractArtistic text style transfer is the task of migrating the style from a source image to the target text to create artistic typography. Recent style transfer methods have considered texture control to enhance usability. However, controlling the stylistic degree in terms of shape deformation remains an important open challenge. In this paper, we present the first text style transfer network that allows for real-time control of the crucial stylistic degree of the glyph through an adjustable parameter. Our key contribution is a novel bidirectional shape matching framework to establish an effective glyph-style mapping at various deformation levels without paired ground truth. Based on this idea, we propose a scale-controllable module to empower a single network to continuously characterize the multi-scale shape features of the style image and transfer these features to the target text. The proposed method demonstrates its superiority over previous state-of-the-arts in generating diverse, controllable and high-quality stylized text.

show abstract

“…To circumvent this issue, [23] propose a deep generative feed-forward network, which allows to synthesize multiple textures within one single network. [13] has demonstrated how control over spatial location, color and across spatial scale leads to enhanced stylized images, where regions are altered by different styles; control over style transfer has been extended to stroke sizes [18]. [26] used a multiscale synthesis pipeline for spatial control and to improve texture quality and stability.…”

Section: Related Workmentioning

confidence: 99%

A Content Transformation Block for Image Style Transfer

Kotovenko

Sanakoyeu

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Style transfer has recently received a lot of attention, since it allows to study fundamental challenges in image understanding and synthesis. Recent work has significantly improved the representation of color and texture and computational speed and image resolution. The explicit transformation of image content has, however, been mostly neglected: while artistic style affects formal characteristics of an image, such as color, shape or texture, it also deforms, adds or removes content details. This paper explicitly focuses on a content-and style-aware stylization of a content image. Therefore, we introduce a content transformation module between the encoder and decoder. Moreover, we utilize similar content appearing in photographs and style samples to learn how style alters content details and we generalize this to other class details. Additionally, this work presents a novel normalization layer critical for high resolution image synthesis. The robustness and speed of our model enables a video stylization in real-time and high definition. We perform extensive qualitative and quantitative evaluations to demonstrate the validity of our approach.

show abstract

Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields

Cited by 101 publications

References 35 publications

Attention-Aware Multi-Stroke Style Transfer

Attention-Aware Multi-Stroke Style Transfer

Controllable Artistic Text Style Transfer via Shape-Matching GAN

A Content Transformation Block for Image Style Transfer

Contact Info

Product

Resources

About