atlas

Research map / Image generation / Editing and style transfer

A Learned Representation For Artistic Style

ICLR 2017 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 876 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
Use one conditional instance normalization network for 10 Monet styles instead of separate single-style networksStyle transfer network · 10 Monet stylescontent loss: 8.7 ± 3.9% higherHurt
Use one conditional instance normalization network for 10 Monet styles instead of separate single-style networksStyle transfer network · 10 Monet stylesstyle loss: 8.9 ± 16.5% lowerNo clear effect
Adapt a trained network by learning style-specific γ and β parameters with shared weights fixed32-style network · Plum Trees in Blossom style adaptationparameter updates for comparable pastiches: 5,000 steps ... 40,000 stepsHelped
Combine styles by convexly interpolating their γ and β parametersConditional instance normalization style representation · Style transfer between Bicentennial Print and Head of a Clownstyle loss with respect to Bicentennial PrintMixed

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