AI Paper Atlas

Research map / Image generation / Editing and style transfer

Controllable Artistic Text Style Transfer via Shape-Matching GAN

Shuai Yang, Zhangyang Wang, Zhaowen Wang, Ning Xu, Jiaying Liu, Zongming Guo

ICCV 2019 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 115 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 glyph network with Controllable ResBlock and texture network to a texture-only baseline (ablation)Shape-Matching GAN · artistic text, maple stylevisual shape consistencyImproved
use Controllable ResBlock instead of label concatenation for scale control (ablation)Glyph network · artistic text, maple stylescale controllabilityImproved
add separate texture network to the glyph network (ablation)Shape-Matching GAN · artistic text, maple styletexture qualityImproved
use Transformation Block in sketch module instead of sigmoid layer (ablation)Sketch module G_B · artistic text, balloon styleshape matchingImproved
add glyph legibility loss (ablation)Shape-Matching GAN · Chinese character, smoke style, high deformationglyph legibilityImproved

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