AI Paper Atlas

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

Learning to Generate Stylized Handwritten Text via a Unified Representation of Style, Content, and Noise

Honglie Wang, Yan-Ming Zhang, Wangzi Yao, Fei Yin, Cheng-Lin Liu

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Text generation and structured prediction

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 aligned positional encoding (APE) over original PE (ablation)InkSpire · IAM English linesFID: 15.12 -> 9.31Improved
add rotation to APE (R-APE) (ablation)InkSpire · IAM English linesFID: 9.31 -> 7.92Improved
add aligned positional encoding (APE) (ablation)InkSpire · ICDAR2013 Chinese linesFID: 17.57 -> 11.75Improved
add rotation to APE (R-APE) (ablation)InkSpire · ICDAR2013 Chinese linesFID: 11.75 -> 10.98Improved
add R-APE on Chinese content accuracy (ablation)InkSpire · ICDAR2013 Chinese linesCR: 89.72 -> 92.92Improved
add R-APE on English Delta CER (ablation)InkSpire · IAM English linesDelta CER: 0.11 -> 0.01Improved
use random-size multi-region masking (R-Mask) instead of fixed top masking (ablation)InkSpire · IAM English linesFID: 8.73 -> 7.92Improved
use R-Mask instead of fixed top masking (ablation)InkSpire · ICDAR2013 Chinese linesFID: 11.57 -> 10.98Improved
use R-Mask instead of F-TopMask on Chinese CR (ablation)InkSpire · ICDAR2013 Chinese linesCR: 92.48 -> 92.92Improved
use frozen pretrained VAE instead of content encoder trained from scratch (ablation)InkSpire · IAM English linesFID: 20.48 -> 7.92Improved
use frozen VAE instead of content+style encoders from scratch (ablation)InkSpire · IAM English linesFID: 17.39 -> 7.92Improved
train content and style encoders from scratch (C+S-Enc) instead of frozen VAE (ablation)InkSpire · ICDAR2013 Chinese linesCR: 92.92 -> 94.74Hurt

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