AI Paper Atlas

Research map / Image generation / Editing and style transfer

StyleGallery: Training-free and Semantic-aware Personalized Style Transfer from Arbitrary Image References

Boyu He, Yunfan Ye, Chang Liu, Weishang Wu, Fang Liu, Zhiping Cai

CVPR 2026 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 0 citations (OpenAlex)

Read the paperCheck 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 regional style loss (RSL) (ablation)StyleGallery · Style-gallery benchmarkLPIPS: 0.5195 -> 0.3716Improved
add regional style loss (RSL) (ablation)StyleGallery · Style-gallery benchmarkStyle: 0.4387 -> 0.5337Improved
add regional style loss (RSL) (ablation)StyleGallery · Style-gallery benchmarkFID: 23.56 -> 16.89Improved
add global content loss (GCL) (ablation)StyleGallery · Style-gallery benchmarkLPIPS: 0.6822 -> 0.3716Improved
add global content loss (GCL) (ablation)StyleGallery · Style-gallery benchmarkFID: 30.83 -> 16.89Improved
add global content loss (GCL) (ablation)StyleGallery · Style-gallery benchmarkStyle: 0.4150 -> 0.5337Improved
raise content loss weight lambda_c from 0.26 to 0.29 (ablation)StyleGallery · Style-gallery benchmarkFID: 16.89 -> 27.26Hurt
raise content loss weight lambda_c from 0.26 to 0.29 (ablation)StyleGallery · Style-gallery benchmarkLPIPS: 0.3716 -> 0.3689No clear effect
lower content loss weight lambda_c from 0.26 to 0.22 (ablation)StyleGallery · Style-gallery benchmarkLPIPS: 0.3716 -> 0.4354Hurt
add semantic mask constraint to style transfer (ablation)StyleGallery · Qualitative examplesleakage (qualitative)Improved
swap SD 1.5 for LCM/Hyper-SD acceleration (ablation)StyleGallery · Qualitative examplesinference time: about 30s -> about 8sImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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