atlas

Research map / Image generation / Editing and style transfer

Preserving Structural Consistency in Arbitrary Artist and Artwork Style Transfer

AAAI 2023 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 3 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 DSTM for arbitrary artist-style and artwork-style transfer from a single artworkStyle transfer on WikiArt · WikiArtDeception rate: 0.589 -> 0.672Helped
Use EEM to preserve structural consistencyPhoto-realistic style transfer · Average across four datasetsFID: 48.74 -> 42.83Helped
Add edge detection to the style-transfer model (ablation)Photo-realistic style transfer · LSUN ChurchFID: 52.34 -> 42.71Helped
Replace EEM edge detection with Canny (ablation)Photo-realistic style transfer · LSUN Church and FFHQFID: 42.71 -> 46.75; 56.98 -> 58.12Hurt
Replace EEM edge detection with FSE (ablation)Photo-realistic style transfer · LSUN Church and FFHQFID: 42.71 -> 48.93; 56.98 -> 58.96Hurt
Add average pooling to the soft edge loss (ablation)EEM · LSUN Church and FFHQFID: 42.66 -> 42.71; 57.02 -> 56.98Mixed
Add reconstruction using only structural component zc (ablation)EEM · LSUN Church and FFHQFID: 45.89 -> 42.71; 57.85 -> 56.98Helped

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