AI Paper Atlas

Research map / Image generation / Editing and style transfer

Learning Dynamic Style Kernels for Artistic Style Transfer

Wenju Xu, Chengjiang Long, Yongwei Nie

CVPR 2023 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 29 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
Use spatially adaptive style kernels generated from content-style aligned features instead of global style modulationStyleKernel · Style transfer evaluationStyle Loss: 1.04 -> 0.98Improved
Add adversarial loss to the attention-based Base model (ablation)StyleKernel · Style transfer evaluationStyle Loss: 2.92 -> 2.14Improved
Add REMD loss to the adversarial-loss variant (ablation)StyleKernel · Style transfer evaluationStyle Loss: 2.14 -> 1.48Improved
Add style kernels to the adversarial- and REMD-loss variant (ablation)StyleKernel · Style transfer evaluationStyle Loss: 1.48 -> 1.11Improved
Add CGM to the style-kernel variant (ablation)StyleKernel · Style transfer evaluationStyle Loss: 1.11 -> 1.08Improved
Add grouped shuffling to the CGM and style-kernel variant (ablation)StyleKernel · Style transfer evaluationStyle Loss: 1.08 -> 0.98Improved
Increase style kernel size from k=3 to k=5 (ablation)StyleKernel · Style transfer evaluationLPIPS: 0.30 -> 0.31Hurt
Increase style kernel size from k=3 to k=5 (ablation)StyleKernel · Style transfer evaluationT512: 0.035 -> 0.044Hurt
Increase style kernel size from k=3 to k=5 (ablation)StyleKernel · Style transfer evaluationStyle Loss: 0.98 -> 0.97Improved
Replace globally shared style modulation with per-position kernels informed by content-style alignmentStyleKernel · Artistic style transfercontent structure preservationImproved
Use CGM to suppress weakly correlated style features during attention aggregation (ablation)StyleKernel · Artistic style transfersemantic region completenessImproved
Use grouped shuffling in the content feature (ablation)StyleKernel · Artistic style transferstyle consistencyImproved

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