DiffusionSTR: Diffusion Model for Scene Text Recognition
This work introduces a novel application of diffusion models to text recognition, addressing the problem of reading text in natural images for computer vision tasks.
The authors tackled scene text recognition by rethinking it as a text-to-text transformation using a diffusion model, achieving competitive accuracy on public datasets.
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.