DynTypo: Example-Based Dynamic Text Effects Transfer

Men, Yifang; Lian, Zhouhui; Tang, Yingmin; Xiao, Jianguo

doi:10.1109/cvpr.2019.00602

Cited by 9 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspired by font generation and texture transfer models ( [3,33,37], and [21,22,36]), we build a text logo synthesis system which takes a desired text and its topic as input and synthesizes the text logo image automatically. Specifically, we first synthesize the font according to the user-input topics, such as lovely, funny, technical, etc.…”

Section: Text Logo Synthesis Systemmentioning

confidence: 99%

“…Then, we send the synthesized glyph images into our layout generation network to synthesize the text logo image. Finally, we perform the texture transfer method proposed by [22] to obtain the final text logo with texture effects. Several examples are shown in Figure 12, demonstrating the effectiveness of our system for synthesizing aesthetic text logos.…”

Section: Text Logo Synthesis Systemmentioning

confidence: 99%

“…Experimental results clearly demonstrate the effectiveness and advantages of our proposed method. We also demonstrate how our proposed model can be integrated with font generation [33] and texture transfer [22] models to automatically synthesize visually-pleasing text logos. To the best of our knowledge, this work presents the first text logo synthesis method that is capable of taking both linguistic (i.e., text contents) and visual (i.e., glyph shapes, font styles, and textures) information into account like professional human designers.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Aesthetic Text Logo Synthesis via Content-aware Layout Inferring

Wang¹,

Guo²,

Luo³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Text logo design heavily relies on the creativity and expertise of professional designers, in which arranging element layouts is one of the most important procedures. However, few attention has been paid to this task which needs to take many factors (e.g., fonts, linguistics, topics, etc.) into consideration. In this paper, we propose a contentaware layout generation network which takes glyph images and their corresponding text as input and synthesizes aesthetic layouts for them automatically. Specifically, we develop a dual-discriminator module, including a sequence discriminator and an image discriminator, to evaluate both the character placing trajectories and rendered shapes of synthesized text logos, respectively. Furthermore, we fuse the information of linguistics from texts and visual semantics from glyphs to guide layout prediction, which both play important roles in professional layout design. To train and evaluate our approach, we construct a dataset named as TextLogo3K, consisting of about 3,500 text logo images and their pixel-level annotations. Experimental studies on this dataset demonstrate the effectiveness of our approach for synthesizing visually-pleasing text logos and verify its superiority against the state of the art.

show abstract