AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition

Xingsong Ye, Yongkun Du, Yunbo Tao, Zhineng Chen

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add region-centric processing (ablation)TextSSR generator · IC13 (ablation)SeqAcc (%): 47.55 -> 82.99Improved
add character-level position prior (ablation)TextSSR generator · IC13 (ablation)SeqAcc (%): 77.21 -> 82.99Improved
add VAE fine-tuning (ablation)TextSSR generator · IC13 (ablation)SeqAcc (%) / FID-R: SeqAcc 80.26 -> 82.99; FID-R 45.83 -> 50.76Mixed
add character-level glyph prior (ablation)TextSSR generator · IC13 (ablation)SeqAcc (%): 76.23 -> 77.21Improved
anagram-based generation instead of equal-length substitution (ablation)TextSSR data · 30k data, CRNN, six benchmarks avgSeqAcc (%): 18.95 -> 50.33Improved
scale TextSSR data from 30k to 240k (ablation)CRNN · six STR benchmarks avgSeqAcc (%): 50.33 -> 64.44Improved
double data to 60k (x2) (ablation)CRNN · six STR benchmarks avgSeqAcc (%): 50.33 -> 50.29No clear effect
increase ST rendered data from 4m to 6.98mCRNN · six STR benchmarks avgSeqAcc (%): 81.90 -> 82.06No clear effect
add 1.05m TextSSR to STCRNN · six STR benchmarks avgSeqAcc (%): 81.90 -> 85.33Improved
add 3.55m TextSSR-F to ST + TextOCRMAERec · six STR benchmarks avgSeqAcc (%): 94.57 -> 95.46Improved
use TextSSR instead of SynthAdd for contextless wordsCRNN · six STR benchmarks avgSeqAcc (%): 81.99 -> 85.33Improved
add TextSSR to ST + TextOCR on SVTPCRNN · SVTPSeqAcc (%): +0.00No clear effect

Later papers that compared with this method

1 later accepted paper reports TextSSR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy