Research map / Image generation / Editing and style transfer
A Content Transformation Block for Image Style Transfer
Check 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 |
|---|---|---|---|
| Add a content transformation block trained to align same-class photo and artwork representations (ablation) | Style transfer model · Person content class, van Gogh | RSSCD (VGG-16): 0.882 -> 0.756 | Helped |
| Add a content transformation block trained to align same-class photo and artwork representations (ablation) | Style transfer model · Person content class, van Gogh | RSSCD (VGG-19): 0.838 -> 0.724 | Helped |
| Add a content transformation block (ablation) | Style transfer model · COCO stylized images | person detection accuracy: 0.598 -> 0.659 | Helped |
| Add a content transformation block (ablation) | Style transfer model · COCO stylized images | person detection recall: 0.209 -> 0.375 | Helped |
| Add a content transformation block (ablation) | Style transfer model · COCO stylized images | person detection precision: 0.937 -> 0.864 | Hurt |
| Add a content transformation block (ablation) | Style transfer model · COCO stylized images | person detection F1-score: 0.343 -> 0.524 | Helped |
| Add a content transformation block trained using the person class (ablation) | Style transfer model · Person stylized patches | deception rate: 0.521 -> 0.618 | Helped |
| Add a content transformation block trained using the person class (ablation) | Style transfer model · Non-person stylized patches | deception rate: 0.541 -> 0.563 | Helped |
| Add a content transformation block trained using the person class (ablation) | Style transfer model · Person stylized patches | non-expert deception score: 0.127 -> 0.210 | Helped |
| Add a content transformation block trained using the person class (ablation) | Style transfer model · Non-person stylized patches | non-expert deception score: 0.143 -> 0.165 | Helped |
| Use local feature normalization instead of omitting LFN (ablation) | Style transfer model · Stylized image regions, especially at higher resolution | visible artifacts | Helped |
Closest papers by meaning
- StyleMaster: Stylize Your Video with Artistic Generation and Translation (CVPR 2025 · similarity 0.89)
- ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation (CVPR 2024 · similarity 0.88)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · similarity 0.88)
- CSGO: Content-Style Composition in Text-to-Image Generation (NeurIPS 2025 · similarity 0.88)
- HSI: A Holistic Style Injector for Arbitrary Style Transfer (CVPR 2025 · similarity 0.88)
- OmniStyle: Filtering High Quality Style Transfer Data at Scale (CVPR 2025 · 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.