Research map / Image generation / Editing and style transfer
EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use exchangeable features by adding the Feature Exchange block and feature exchange loss (ablation) | EFANet · 100 test images | Style loss: 22.6713 -> 14.8582 | Helped |
| Use exchangeable features by adding the Feature Exchange block and feature exchange loss (ablation) | EFANet · 100 test images | Content loss: 16.3763 -> 16.5927 | Mixed |
| Use multi-scale fusion instead of fusing only at relu_4 (ablation) | EFANet · 100 test images | Style loss: 24.9123 -> 14.8582 | Helped |
| Remove the learnable whitening matrices and whitening loss (ablation) | EFANet · Style transfer examples | Visual style and structure quality | Hurt |
| Use multi-scale fusion instead of single-scale fusion at relu_4 (ablation) | EFANet · Style transfer examples | Salient style-pattern capture | Helped |
| Use EFANet instead of AdaIN | Arbitrary style transfer · 100 test images | Content loss: 14.4226 -> 16.5927 | Hurt |
| Use EFANet instead of AdaIN | Arbitrary style transfer · 100 test images | Style loss: 40.5989 -> 14.8582 | Helped |
| Use EFANet instead of WCT | Arbitrary style transfer · 100 test images | Preference score: 0.155 -> 0.200 | Helped |
| Use EFANet instead of Li et al. | Arbitrary style transfer · 256 × 256 test images | Time/sec: 0.0071 -> 0.0234 | Hurt |
Closest papers by meaning
- Universal Style Transfer via Feature Transforms (NeurIPS 2017 · similarity 0.89)
- OmniStyle: Filtering High Quality Style Transfer Data at Scale (CVPR 2025 · similarity 0.86)
- CLeaR: A Unified Framework for Resolving the Leakage–Degradation Dilemma in Style Transfer (NeurIPS 2026 · similarity 0.86)
- StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements (CVPR 2025 · similarity 0.86)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · similarity 0.86)
- Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network (CVPR 2024 · similarity 0.85)
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.