Improving Diffusion Models for Scene Text Editing with Dual Encoders

Published: 29 Apr 2024, Last Modified: 17 Sept 2024Accepted by TMLREveryoneRevisionsBibTeXCC BY 4.0
Abstract: Scene text editing is a challenging task that involves modifying or inserting specified texts in an image while maintaining its natural and realistic appearance. Most previous approaches to this task rely on style-transfer models that crop out text regions and feed them into image transfer models, such as GANs. However, these methods are limited in their ability to change text style and are unable to insert texts into images. Recent advances in diffusion models have shown promise in overcoming these limitations with text-conditional image editing. However, our empirical analysis reveals that state-of-the-art diffusion models struggle with rendering correct text and controlling text style. To address these problems, we propose DIFFSTE to improve pre-trained diffusion models with a dual encoder design, which includes a character encoder for better text legibility and an instruction encoder for better style control. An instruction tuning framework is introduced to train our model to learn the mapping from the text instruction to the corresponding image with either the specified style or the style of the surrounding texts in the background. Such a training method further brings our method the zero-shot generalization ability to the following three scenarios: generating text with unseen font variation, e.g., italic and bold, mixing different fonts to construct a new font, and using more relaxed forms of natural language as the instructions to guide the generation task. We evaluate our approach on five datasets and demonstrate its superior performance in terms of text correctness, image naturalness, and style controllability.
Submission Length: Regular submission (no more than 12 pages of main content)
Previous TMLR Submission Url: https://openreview.net/forum?id=XR57KdQeA0
Changes Since Last Submission: Update to camera ready version.
Code: https://github.com/UCSB-NLP-Chang/DiffSTE
Supplementary Material: zip
Assigned Action Editor: ~Hongsheng_Li3
Submission Number: 1536
Loading