AI Paper Atlas

Research map / Image generation / Editing and style transfer

Controlling Perceptual Factors in Neural Style Transfer

Leon A. Gatys, Alexander S. Ecker, Matthias Bethge, Aaron Hertzmann, Eli Shechtman

CVPR 2017 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 520 citations (OpenAlex)

Check 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 spatial guidance with eroded region masks and a global guidance channelNeural Style Transfer · Spatially guided image stylisationregion-specific stylisation qualityImproved
Use spatial guidance to match corresponding regions in content and style imagesNeural Style Transfer · Sky and ground stylisationcross-region texture artefactsImproved
Replace guided Gram Matrices with the guided-sums representation (ablation)Spatially guided Neural Style Transfer · Spatially guided image stylisationtexture qualityHurt
Preserve content-image colours by transferring style in luminance onlyNeural Style Transfer · Colour-preserving stylisationcontent-colour preservationImproved
Use luminance-only transfer instead of colour matching (ablation)Neural Style Transfer · Styles with prominent brushstrokesbrushstroke colour naturalnessHurt
Match style-image colours to content-image colours before style transferNeural Style Transfer · Colour-preserving stylisationcolour preservationImproved
Replace full-image style transfer with luminance-only transfer (ablation)Neural Style Transfer · Colour-preserving stylisationluminance-colour dependency preservationHurt
Construct a style image by transferring fine-scale style onto coarse-scale styleNeural Style Transfer · Style mixing across spatial scalesindependent scale controlImproved
Use low-resolution stylisation followed by upsampling and high-resolution refinementNeural Style Transfer · High-resolution stylisationhigh-resolution optimisation iterations: 2.5 times fewer iterationsImproved
Use a luminance-trained feed-forward network instead of combining luminance output from a regular network with content colour (ablation)Fast Neural Style Transfer · Colour-preserving stylisationintegration of stylisation with content structuresImproved
Train spatially guided feed-forward stylisation with fixed guidance masks, then use arbitrary masks at test timeFast Neural Style Transfer · Spatially guided stylisationguidance-mask generalisationImproved

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