AI Paper Atlas

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

DiffusionPen: Towards Controlling the Style of Handwritten Text Generation

Konstantina Nikolaidou, George Retsinas, Giorgos Sfikas, Marcus Liwicki

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 41 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
use hybrid classification plus triplet style encoder instead of classification only (ablation)DiffusionPen · IAM writer classificationaccuracy (%): 68.04 -> 70.31Improved
use hybrid classification plus triplet style encoder instead of triplet only (ablation)DiffusionPen · IAM writer classificationaccuracy (%): 67.50 -> 70.31Improved
use hybrid style encoder instead of classification only for FID (ablation)DiffusionPen · IAM generated wordsFID: 22.23 -> 22.54No clear effect
use hybrid style encoder instead of classification only for HTR imitation (ablation)DiffusionPen · HTR on synthetic IAMCER (%): 7.12 -> 6.94Improved
condition on few-shot style embedding from 5 samples instead of class embedding (WordStylist)latent diffusion HTG · HTR on synthetic IAMCER (%): 8.26 -> 6.94Improved
add small style-embedding noise (0.25) (ablation)DiffusionPen · HTR on synthetic IAMCER (%): 6.94 -> 6.79Improved
increase style-embedding noise to 2.00 (ablation)DiffusionPen · HTR on synthetic IAMCER (%): 6.79 -> 7.56 (0.25 vs 2.00)Hurt
add noise bias in the diffusion prior (ablation)DiffusionPen · HTR on synthetic IAMCER (%): 6.94 -> 6.93No clear effect
augment real IAM training with 55K DiffusionPen samplesCNN-LSTM HTR · IAM word-level HTRCER (%): 5.14 -> 4.71Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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