AI Paper Atlas

Research map / Image generation / Editing and style transfer

TET-GAN: Text Effects Transfer via Stylization and Destylization

Shuai Yang, Jiaying Liu, Wenjing Wang, Zongming Guo

AAAI 2019 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 82 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 reconstruction and feature losses (ablation)TET-GAN · Text effects transfervisual transfer qualityImproved
Add feature loss to guide content-feature extraction (ablation)TET-GAN · Text effects transferglyph disentanglement and artifact qualityImproved
Add distribution-aware text-image preprocessing and text-effects augmentation (ablation)TET-GAN · Text effects transfertexture placement qualityImproved
Replace Batch Normalization with Instance Normalization in the text-effects content encoderTET-GAN destylization subnetwork · Destylizationdestylization qualityImproved
Pretrain on the text-effects dataset before one-shot finetuningTET-GAN · One-shot supervised style transferstylization qualityImproved
Use the proposed self-stylization finetuning schemeTET-GAN · One-shot supervised style transferinference time: one minute per image -> 20ms per imageImproved
Add common style autoencoder reconstruction or cycle-consistency losses (ablation)TET-GAN stylization subnetwork · Text effects transferstylization resultsNo clear effect
Use pixel-domain patch matchingT-Effect · Text effects transfercolor continuityHurt
Use greedy deep-feature patch matchingNeural Doodles · Text effects transferglyph shape preservationHurt
Train TET-GAN from scratch rather than pretraining it on the proposed dataset (ablation)TET-GAN · One-shot supervised style transferstylization qualityHurt

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