Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing

TL;DR

This paper introduces DARLING, a framework that disentangles style and content features in scene text images, enabling improved performance across recognition, removal, and editing tasks by explicitly separating these features.

Contribution

The paper presents the first approach to disentangle style and content features in scene text images, enhancing adaptability for various downstream tasks.

Findings

Achieves state-of-the-art results in scene text recognition.

Improves scene text removal and editing performance.

Effectively decouples style and content features in images.

Abstract

Scene text images contain not only style information (font, background) but also content information (character, texture). Different scene text tasks need different information, but previous representation learning methods use tightly coupled features for all tasks, resulting in sub-optimal performance. We propose a Disentangled Representation Learning framework (DARLING) aimed at disentangling these two types of features for improved adaptability in better addressing various downstream tasks (choose what you really need). Specifically, we synthesize a dataset of image pairs with identical style but different content. Based on the dataset, we decouple the two types of features by the supervision design. Clearly, we directly split the visual representation into style and content features, the content features are supervised by a text recognition loss, while an alignment loss aligns the style features in the image pairs. Then, style features are employed in reconstructing the counterpart image via an image decoder with a prompt that indicates the counterpart's content. Such an operation effectively decouples the features based on their distinctive properties. To the best of our knowledge, this is the first time in the field of scene text that disentangles the inherent properties of the text images. Our method achieves state-of-the-art performance in Scene Text Recognition, Removal, and Editing.