atlas

Research map / Image generation / Editing and style transfer

Image Style Transfer Using Convolutional Neural Networks

CVPR 2016 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 6,164 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
Use a higher content layer, conv4_2 instead of conv2_2 (ablation)Neural Algorithm of Artistic Style · Image style transfercontent-style integrationHelped
Match style features across more layers, through conv5_1 (ablation)Neural Algorithm of Artistic Style · Image style transfervisual smoothnessHelped
Increase the relative weight of style matching (ablation)Neural Algorithm of Artistic Style · Image style transferstyle matchingMixed
Increase the relative weight of content matching (ablation)Neural Algorithm of Artistic Style · Image style transfercontent matchingMixed
Initialize optimization from the content image or style image instead of white noise (ablation)Neural Algorithm of Artistic Style · Image style transfersynthesis outcomeNo clear effect
Replace max pooling with average pooling (ablation)VGG-19 used for image synthesis · Image synthesisvisual appealHelped
Add image priors to regularize synthesis (ablation)Neural Algorithm of Artistic Style · Image style transferimage qualityNo clear effect

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