Type-R: Automatically Retouching Typos for Text-to-Image Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shimoda, Wataru, Inoue, Naoto, Haraguchi, Daichi, Mitani, Hayato, Uchida, Seiichi, Yamaguchi, Kota
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915266207678464
author Shimoda, Wataru
Inoue, Naoto
Haraguchi, Daichi
Mitani, Hayato
Uchida, Seiichi
Yamaguchi, Kota
author_facet Shimoda, Wataru
Inoue, Naoto
Haraguchi, Daichi
Mitani, Hayato
Uchida, Seiichi
Yamaguchi, Kota
contents While recent text-to-image models can generate photorealistic images from text prompts that reflect detailed instructions, they still face significant challenges in accurately rendering words in the image. In this paper, we propose to retouch erroneous text renderings in the post-processing pipeline. Our approach, called Type-R, identifies typographical errors in the generated image, erases the erroneous text, regenerates text boxes for missing words, and finally corrects typos in the rendered words. Through extensive experiments, we show that Type-R, in combination with the latest text-to-image models such as Stable Diffusion or Flux, achieves the highest text rendering accuracy while maintaining image quality and also outperforms text-focused generation baselines in terms of balancing text accuracy and image quality.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18159
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Type-R: Automatically Retouching Typos for Text-to-Image Generation
Shimoda, Wataru
Inoue, Naoto
Haraguchi, Daichi
Mitani, Hayato
Uchida, Seiichi
Yamaguchi, Kota
Computer Vision and Pattern Recognition
While recent text-to-image models can generate photorealistic images from text prompts that reflect detailed instructions, they still face significant challenges in accurately rendering words in the image. In this paper, we propose to retouch erroneous text renderings in the post-processing pipeline. Our approach, called Type-R, identifies typographical errors in the generated image, erases the erroneous text, regenerates text boxes for missing words, and finally corrects typos in the rendered words. Through extensive experiments, we show that Type-R, in combination with the latest text-to-image models such as Stable Diffusion or Flux, achieves the highest text rendering accuracy while maintaining image quality and also outperforms text-focused generation baselines in terms of balancing text accuracy and image quality.
title Type-R: Automatically Retouching Typos for Text-to-Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.18159