Research map / Image generation / Editing and style transfer
Universal Style Transfer via Feature Transforms
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 WCT rather than the compared methods | Universal style transfer with VGG-19 · Style transfer | log(L_s): 6.7 -> 6.3 | Helped |
| Use WCT rather than the compared methods | Universal style transfer with VGG-19 · Style transfer | user preference (%): 16.4 -> 30.3 | Helped |
| Use WCT rather than Gatys et al. | Universal style transfer · Style transfer, 256×256 images | time (sec): 21.2 -> 0.83 | Helped |
| Use WCT instead of channel-wise histogram matching (ablation) | Feature-based style transfer · Style transfer | visual capture of salient style patterns | Helped |
| Process feature layers coarse-to-fine rather than fine-to-coarse (ablation) | Multi-level WCT stylization · Style transfer | preservation of low-level information | Helped |
| Apply WCT sequentially at multiple feature levels rather than a single level (ablation) | WCT stylization · Style transfer | visual quality | Helped |
| Initialize features with white noise instead of using a random-noise content image (ablation) | WCT texture synthesis · Texture synthesis | visual result quality | No clear effect |
Closest papers by meaning
- A Content Transformation Block for Image Style Transfer (CVPR 2019 · similarity 0.92)
- Learning Linear Transformations for Fast Image and Video Style Transfer (CVPR 2019 · similarity 0.92)
- OmniStyle: Filtering High Quality Style Transfer Data at Scale (CVPR 2025 · similarity 0.88)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · similarity 0.88)
- Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network (CVPR 2024 · similarity 0.88)
- Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer (CVPR 2024 · similarity 0.88)
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.