DiffusionSTR: Diffusion Model for Scene Text Recognition

TL;DR

This paper introduces DiffusionSTR, a novel scene text recognition framework that applies diffusion models to recognize text in images, achieving competitive accuracy with existing methods.

Contribution

It is the first to apply diffusion models to scene text recognition, rethinking the task as a text-text transformation under images.

Findings

Achieves competitive accuracy on public datasets

First application of diffusion models to text recognition

Reframes scene text recognition as a diffusion-based text-to-text task

Abstract

This paper presents Diffusion Model for Scene Text Recognition (DiffusionSTR), an end-to-end text recognition framework using diffusion models for recognizing text in the wild. While existing studies have viewed the scene text recognition task as an image-to-text transformation, we rethought it as a text-text one under images in a diffusion model. We show for the first time that the diffusion model can be applied to text recognition. Furthermore, experimental results on publicly available datasets show that the proposed method achieves competitive accuracy compared to state-of-the-art methods.