# TE141K: Artistic Text Benchmark for Text Effect Transfer

## TL;DR

This paper introduces TE141K, the largest dataset for text effect transfer, and proposes TET-GAN, a model that effectively transfers 152 styles across multiple languages, advancing automatic artistic text rendering.

## Contribution

The paper provides the first large-scale dataset TE141K for text effect transfer and develops TET-GAN, a versatile model supporting multi-style transfer and easy extension to new styles.

## Key findings

- TET-GAN outperforms 14 benchmark models qualitatively and quantitatively.
- TE141K dataset contains 141,081 text effect/glyph pairs across multiple languages.
- The dataset is effective and challenging for text effect transfer tasks.

## Abstract

Text effects are combinations of visual elements such as outlines, colors and textures of text, which can dramatically improve its artistry. Although text effects are extensively utilized in the design industry, they are usually created by human experts due to their extreme complexity; this is laborious and not practical for normal users. In recent years, some efforts have been made toward automatic text effect transfer; however, the lack of data limits the capabilities of transfer models. To address this problem, we introduce a new text effects dataset, TE141K, with 141,081 text effect/glyph pairs in total. Our dataset consists of 152 professionally designed text effects rendered on glyphs, including English letters, Chinese characters, and Arabic numerals. To the best of our knowledge, this is the largest dataset for text effect transfer to date. Based on this dataset, we propose a baseline approach called text effect transfer GAN (TET-GAN), which supports the transfer of all 152 styles in one model and can efficiently extend to new styles. Finally, we conduct a comprehensive comparison in which 14 style transfer models are benchmarked. Experimental results demonstrate the superiority of TET-GAN both qualitatively and quantitatively and indicate that our dataset is effective and challenging.