atlas

Research map / Image generation / Autoregressive and latent generation

Handwritten Text Generation From Visual Archetypes

CVPR 2023 · Image generation › Autoregressive and latent generation · approach: Synthetic training data from generators · 52 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 VATr-generated images to real-data HTR trainingHTR model · Saint GallWER: 32.5 -> 30.9Helped
Add VATr-generated images to real-data HTR trainingHTR model · Saint GallCER: 4.5 -> 4.5No clear effect
Add VATr-generated images to real-data HTR trainingHTR model · WashingtonCER: 3.4 -> 3.0Helped
Add VATr-generated images to real-data HTR trainingHTR model · WashingtonWER: 15.9 -> 13.1Helped
Add L_HTR text-recognition loss (ablation)VATr · IAM word 'that', two stylesFID: 220.83 -> 17.79Helped
Add L_class writer-classification loss (ablation)VATr · IAM word 'that', two stylesFID: 41.68 -> 17.79Helped
Add L_cycle cycle loss (ablation)VATr · IAM word 'that', two stylesFID: 18.70 -> 17.79Helped

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