Paper Image

Manipulating text in images

Published on:

1 November 2023

Primary Category:

Computer Vision and Pattern Recognition

Paper Authors:

Joshua Santoso,

Christian Simon,

Williem Pao


Key Details

Proposes a novel diffusion model to manipulate text in images

Performs one-shot adaptation to preserve style of original image

Uses text recognition guidance for higher accuracy

Achieves state of the art performance on scene text datasets

Enables applications like sign translation and privacy protection

AI generated summary

Manipulating text in images

This paper proposes a new deep learning method to edit the text in images of real-world scenes. The method can replace existing text with new text, while preserving the visual style and layout of the original image. This enables applications like translating text signs without altering their appearance.

Answers from this paper


No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up