AI Paper Atlas

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

Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

Xingsong Ye, Yongkun Du, Jiaxin Zhang, Haojie Zhang, Chong Sun, Chen Li, Jing LYU, Zhineng Chen

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 1 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 2M WATER-S synthetic data to real WATER-R training data (ablation)WATERec · WordArt-Benchaccuracy (%): 88.55 -> 90.40Improved
add WATER-S to real data across architectures (ablation)SVTRv2 / ABINet / SVTRv2-AR · WordArt-Benchaccuracy (%): 86.56 -> 88.68; 84.64 -> 87.03; 87.36 -> 90.14Improved
scale WATER-S from 2M to 3M (ablation)WATERec · WordArt-Benchaccuracy (%): 90.40 -> 90.07No clear effect
combine 0.5M WATER-T and 0.5M WATER-Z instead of 1M of either (ablation)WATERec · WordArt-Benchaccuracy (%): 89.94 vs 89.81 (T) and 89.41 (Z)Improved
use WATER-T instead of SynthText or SynthTIGER (1M each) (ablation)WATERec · WordArt-Benchaccuracy (%): 89.81 vs 88.95 and 88.55Improved
use WATER-Z instead of TextSSR (1M each) (ablation)WATERec · WordArt-Benchaccuracy (%): 89.41 vs 88.09Improved
remove position encoding under arbitrary-shape input (ablation)WATERec · WordArt-Benchaccuracy (%): 88.55 -> 49.57Hurt
use RoPE instead of APE or SPE with arbitrary-shape input (ablation)WATERec · WordArt-Benchaccuracy (%): 87.69 (APE), 87.29 (SPE) -> 88.55Improved
allow arbitrary-shape input instead of fixed 256 tokens (with RoPE) (ablation)WATERec · Union14M-Benchmark AVGaccuracy (%): 86.99 -> 88.14Improved
raise token range upper bound from 256 to 512 (ablation)WATERec · WordArt-Benchaccuracy (%): 88.55 -> 88.82Improved
use arbitrary-shape input and AR decoder instead of fixed resolutionWATERec vs MAERec · Common benchmarks AVGaccuracy (%): 96.96 (MAERec) vs 96.69Hurt

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