Layout Agnostic Scene Text Image Synthesis with Diffusion Models
This addresses the problem of limited text style diversity in scene text image synthesis for computer vision researchers, though it appears incremental as it builds on existing diffusion models.
The paper tackles the challenge of generating scene text images with diffusion models by eliminating the need for intermediate layout generation, which constrained text style diversity. Their SceneTextGen model achieved improved character recognition rates on public datasets compared to existing diffusion-based and text-specific methods.
While diffusion models have significantly advanced the quality of image generation their capability to accurately and coherently render text within these images remains a substantial challenge. Conventional diffusion-based methods for scene text generation are typically limited by their reliance on an intermediate layout output. This dependency often results in a constrained diversity of text styles and fonts an inherent limitation stemming from the deterministic nature of the layout generation phase. To address these challenges this paper introduces SceneTextGen a novel diffusion-based model specifically designed to circumvent the need for a predefined layout stage. By doing so SceneTextGen facilitates a more natural and varied representation of text. The novelty of SceneTextGen lies in its integration of three key components: a character-level encoder for capturing detailed typographic properties coupled with a character-level instance segmentation model and a word-level spotting model to address the issues of unwanted text generation and minor character inaccuracies. We validate the performance of our method by demonstrating improved character recognition rates on generated images across different public visual text datasets in comparison to both standard diffusion based methods and text specific methods.