AI Paper Atlas

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

VATr++: Choose Your Words Wisely for Handwritten Text Generation

Bram Vanherle, Vittorio Pippi, Silvia Cascianelli, Nick Michiels, Frank Van Reeth, Rita Cucchiara

TPAMI 2024 · Image generation › Text-to-image diffusion · approach: Text generation and structured prediction · 29 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 style input preparation (drop singleton punctuation style images) (ablation)VATr++ · IAM Test, long-tail wordsFID: without it +0.96Improved
add style input preparation (ablation)VATr++ · IAM Test, all wordsFID: without it -0.44Hurt
add style input preparation (ablation)VATr++ · Balanced/IAM TestCER: without it +0.30Improved
add text input preparation (rare-character augmentation) (ablation)VATr++ · IAM TestCER: without it +4.45Improved
add text input preparation (ablation)VATr++ · IAM Test, all wordsFID: without it +0.06No clear effect
add discriminator regularization (random crop) (ablation)VATr++ · IAM Test, long-tail wordsFID: without it +2.77Improved
add discriminator regularization (ablation)VATr++ · IAM Test, all wordsFID: without it +2.70Improved
add HTR model regularization (random transforms) (ablation)VATr++ · IAM Test, long-tail wordsFID: without it +2.03Improved
add HTR model regularization (ablation)VATr++ · IAM TestCER: without it -0.39Hurt
upgrade VATr to VATr++VATr++ · IAM-W16FID: 17.55 -> 16.29Improved
upgrade VATr to VATr++VATr++ · IAM-L (line-level)FID: 22.66 -> 24.51Hurt
upgrade VATr to VATr++VATr++ · IAM long-tail words (TrOCR)CER: 5.73 -> 2.34Improved

Later papers that compared with this method

6 later accepted papers report VATr++ as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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