AI Paper Atlas

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

IPAD: Iterative, Parallel, and Diffusion-Based Network for Scene Text Recognition

Xiaomeng Yang, Zhi Qiang Qiao, Yu Zhou

IJCV 2025 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 22 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 easy-first iterative decoding (ablation)parallel decoder baseline · English synthetic7248-sample avg accuracy: 92.00 -> 92.47Improved
add easy-first iterative decoding (ablation)parallel decoder baseline · BCTR Chineseaccuracy: 80.56 -> 82.78Improved
add discrete diffusion training (ablation)IPAD w/o · English synthetic7248-sample avg accuracy: 92.47 -> 93.25Improved
add discrete diffusion training (ablation)IPAD w/o · English real7248-sample avg accuracy: 95.85 -> 96.39Improved
add discrete diffusion training (ablation)IPAD w/o · BCTR Chineseaccuracy: 82.78 -> 84.08Improved
add mimicking learning instead of diffusion (ablation)IPAD w/o · English real7248-sample avg accuracy: 95.85 -> 95.94No clear effect
replace CNN encoder with ViT encoder (ablation)PIMNet · Six English benchmarksavg accuracy: 90.5 -> 92.6Improved
add mimicking learning with ViT encoder (ablation)IPAD w/o · Six English benchmarksavg accuracy: 92.5 -> 92.6No clear effect
add timestep embedding (sinusoidal T=25) (ablation)IPAD · BCTR Chineseaccuracy: 81.97 -> 84.08Improved
use sinusoidal timestep embedding instead of learnable embedding (ablation)IPAD · BCTR Chineseaccuracy: 82.65 -> 84.08Improved
increase easy-first iterations from 1 to 5 (ablation)IPAD · English syntheticavg accuracy: 92.15 -> 93.25Improved
increase iterations from 5 to 25 (ablation)IPAD · English realavg accuracy: 96.39 -> 96.27No clear effect

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