AI Paper Atlas

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

Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation

Gang Dai, Yifan Zhang, Yutao Qin, Qiangya Guo, Shuangping Huang, Shuicheng Yan

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Text generation and structured prediction · 11 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 column- and row-wise masked style module (vs no masking) (ablation)DiffBrush · IAMHWD: 1.82 -> 1.47Improved
use column/row-wise masking instead of random masking (ablation)DiffBrush · IAMHWD: 1.75 -> 1.47Improved
add line and word content discriminators (ablation)DiffBrush · IAMD_CERImproved
use content discriminators instead of CTC recognizer (ablation)DiffBrush · IAMHWD: 1.67 -> 1.41Improved
use content discriminators instead of CTC recognizer (ablation)DiffBrush · IAMD_CER: 16.53 -> 8.59Improved
use 3D CNN line discriminator instead of 2D (ablation)DiffBrush · IAMD_CER: 13.18 -> 8.59Improved
switch word discriminator from 2D to 3D CNN (ablation)DiffBrush · IAMD_CER: 8.59 -> 9.58No clear effect
set masking ratio to 0.5 instead of 0 (ablation)DiffBrush w/o discriminators · IAMHWD: 1.72 -> 1.47Improved
set masking ratio to 0.75 instead of 0.5 (ablation)DiffBrush w/o discriminators · IAMHWD: 1.47 -> 1.58Hurt
generate whole text-lines directly instead of assembling One-DM wordsDiffBrush · IAMHWD: 2.17 -> 1.41Improved
set content loss weight lambda to 0.05 instead of 0.1 (ablation)DiffBrush · IAMD_CER: 9.87 -> 8.59Improved
add DiffBrush synthetic data to recognizer trainingOCR recognizer · IAM testrelative improvement: 20.07%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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