Scene text editing (STE), which converts a text in a scene image into the desired text while preserving an original style, is a challenging task due to a complex intervention between text and style. In this paper, we propose a novel STE model, referred to as RewriteNet, that decomposes text images into content and style features and re-writes a text in the original image. Specifically, RewriteNet implicitly distinguishes the content from the style by introducing scene text recognition. Additionally, independent of the exact supervisions with synthetic examples, we propose a self-supervised training scheme for unlabeled real-world images, which bridges the domain gap between synthetic and real data. Our experiments present that RewriteNet achieves better generation performances than other comparisons. Further analysis proves the feature decomposition of RewriteNet and demonstrates the reliability and robustness through diverse experiments. Our implementation is publicly available at \url{https://github.com/clovaai/rewritenet}
@article{arxiv.2107.11041,
title = {RewriteNet: Reliable Scene Text Editing with Implicit Decomposition of Text Contents and Styles},
author = {Junyeop Lee and Yoonsik Kim and Seonghyeon Kim and Moonbin Yim and Seung Shin and Gayoung Lee and Sungrae Park},
journal= {arXiv preprint arXiv:2107.11041},
year = {2022}
}