English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Current text recognition systems, including those for handwritten scripts andscene text, have relied heavily on image synthesis and augmentation, since itis difficult to realize real-world complexity and diversity through collectingand annotating enough real text images. In this paper, we explore the problemof text image generation, by taking advantage of the powerful abilities ofDiffusion Models in generating photo-realistic and diverse image samples withgiven conditions, and propose a method called Conditional Text Image Generationwith Diffusion Models (CTIG-DM for short). To conform to the characteristics oftext images, we devise three conditions: image condition, text condition, andstyle condition, which can be used to control the attributes, contents, andstyles of the samples in the image generation process. Specifically, four textimage generation modes, namely: (1) synthesis mode, (2) augmentation mode, (3)recovery mode, and (4) imitation mode, can be derived by combining andconfiguring these three conditions. Extensive experiments on both handwrittenand scene text demonstrate that the proposed CTIG-DM is able to produce imagesamples that simulate real-world complexity and diversity, and thus can boostthe performance of existing text recognizers. Besides, CTIG-DM shows itsappealing potential in domain adaptation and generating images containingOut-Of-Vocabulary (OOV) words.

Conditional Text Image Generation with Diffusion Models