TE141K: Artistic Text Benchmark for Text Effect Transfer

Yang, Shuai; Wang, Wenjing; Liu, Jiaying

doi:10.1109/tpami.2020.2983697

Cited by 18 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The font style (text effect) transfer is a subtopic of general image style transfer [40]. Recent works [41], [42], [43], [44], [45], [46], [47] have intensively studied the text effect on a printed single character and achieved great success. However, these approaches cannot be directly deployed for handwriting synthesis.…”

Section: Font Style Transfermentioning

confidence: 99%

“…The number of font styles is relatively limited. For instance, the representative benchmark, TE141K [45], comprised only 152 font effects, whereas the handwriting dataset IAM [3] was collected from 657 writers. Third, previous studies focused on the effects of only a single character, however, a handwritten text image typically contains multiple characters.…”

Section: Font Style Transfermentioning

confidence: 99%

See 1 more Smart Citation

SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text

Luo¹,

Zhu²,

Jin³

et al. 2022

Preprint

View full text Add to dashboard Cite

Large amounts of labeled data are urgently required for the training of robust text recognizers. However, collecting handwriting data of diverse styles, along with an immense lexicon, is considerably expensive. Although data synthesis is a promising way to relieve data hunger, two key issues of handwriting synthesis, namely, style representation and content embedding, remain unsolved. To this end, we propose a novel method that can synthesize parameterized and controllable handwriting Styles for arbitrary-Length and Out-of-vocabulary text based on a Generative Adversarial Network (GAN), termed SLOGAN. Specifically, we propose a style bank to parameterize the specific handwriting styles as latent vectors, which are input to a generator as style priors to achieve the corresponding handwritten styles. The training of the style bank requires only the writer identification of the source images, rather than attribute annotations. Moreover, we embed the text content by providing an easily obtainable printed style image, so that the diversity of the content can be flexibly achieved by changing the input printed image. Finally, the generator is guided by dual discriminators to handle both the handwriting characteristics that appear as separated characters and in a series of cursive joins. Our method can synthesize words that are not included in the training vocabulary and with various new styles. Extensive experiments have shown that high-quality text images with great style diversity and rich vocabulary can be synthesized using our method, thereby enhancing the robustness of the recognizer.

show abstract

Section: Font Style Transfermentioning

confidence: 99%

Section: Font Style Transfermentioning

confidence: 99%

SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text

Luo¹,

Zhu²,

Jin³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Transferring artistic text font and texture while maintaining content information is extremely challenging. There are many efforts [40,37,20,39,35,38,36] to migrate text style from some given character information. Some work focused on text editing, for instance, [31] trained an SRNet to edit text styles in natural images.…”

Section: Text Style Transfermentioning

confidence: 99%

“…To validate the effectiveness of our proposed method, we implement our model to perform the ablation study on a recently released artistic text benchmark [37]. For traditional artistic effect rendering task, our model achieves the best record compared with the unsupervised image style transfer models.…”

Section: Introductionmentioning

confidence: 99%

GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation

Huang¹,

Fu²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Automatic artistic text generation is an emerging topic which receives increasing attention due to its wide applications. The artistic text can be divided into three components, content, font, and texture, respectively. Existing artistic text generation models usually focus on manipulating one aspect of the above components, which is a sub-optimal solution for controllable general artistic text generation. To remedy this issue, we propose a novel approach, namely GenText, to achieve general artistic text style transfer by separably migrating the font and texture styles from the different source images to the target images in an unsupervised manner. Specifically, our current work incorporates three different stages, stylization, destylization, and font transfer, respectively, into a unified platform with a single powerful encoder network and two separate style generator networks, one for font transfer, the other for stylization and destylization. The destylization stage first extracts the font style of the font reference image, then the font transfer stage generates the target content with the desired font style. Finally, the stylization stage renders the resulted font image with respect to the texture style in the reference image. Moreover, considering the difficult data acquisition of paired artistic text images, our model is designed under the unsupervised setting, where all stages can be effectively optimized from unpaired data. Qualitative and quantitative results are performed on artistic text benchmarks, which demonstrate the superior performance of our proposed model. The code with models will become publicly available in the future.

show abstract

“…With the development of the neural style transfer field, in addition to the study of artistic style transfer, other aspects of style transfer techniques are also of interest, such as style transfer of highresolution images, which is used to process HD images, 15,16 text style transfer that changes text attributes 17,18 and photorealistic style transfer between real images. 19,20 Traditional methods of photorealistic style transfer are mainly based on color and tone matching.…”

Section: Introductionmentioning

confidence: 99%

UMFA: A photorealistic style transfer method based on U-Net and multi-layer feature aggregation

Rao,

Wu,

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we propose a photorealistic style transfer network to emphasize the natural effect of photorealistic image stylization. In general, distortion of the image content and lacking of details are two typical issues in the style transfer field. To this end, we design a novel framework employing the U-Net structure to maintain the rich spatial clues, with a multi-layer feature aggregation (MFA) method to simultaneously provide the details obtained by the shallow layers in the stylization processing. In particular, an encoder based on the dense block and a decoder form a symmetrical structure of U-Net are jointly staked to realize an effective feature extraction and image reconstruction. Besides, a transfer module based on MFA and "adaptive instance normalization" (AdaIN) is inserted in the skip connection positions to achieve the stylization. Accordingly, the stylized image possesses the texture of a real photo and preserves rich content details without introducing any mask or post-processing steps. The experimental results on public datasets demonstrate that our method achieves a more faithful structural similarity with a lower style loss, reflecting the effectiveness and merit of our approach.

show abstract

TE141K: Artistic Text Benchmark for Text Effect Transfer

Cited by 18 publications

References 26 publications

SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text

SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text

GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation

UMFA: A photorealistic style transfer method based on U-Net and multi-layer feature aggregation

Contact Info

Product

Resources

About