atlas

Research map / Image generation / Editing and style transfer

DualAST: Dual Style-Learning Networks for Artistic Style Transfer

CVPR 2021 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 75 citations (OpenAlex)

Check 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
learn holistic artist-style and specific artwork-style jointlyDualAST · User studyVisual quality: 0.305Helped
learn holistic artist-style and specific artwork-style jointlyDualAST · User studyStyle controllability: 0.182Mixed
remove holistic artist-style learning (ablation)DualAST · Artistic style transferVisual qualityHurt
add specific artwork-style learning from the reference image (ablation)DualAST · Artistic style transferStyle controllabilityHelped
add the style-aware content adversarial loss (ablation)DualAST · Artistic style transferContent preservationHelped
replace the Style-Control Block with a concatenation layer (ablation)DualAST · Artistic style transferStyle transfer qualityHurt
replace the Style-Control Block with AdaIN (ablation)DualAST · Artistic style transferStyle transfer 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