Research map / Image generation / Editing and style transfer
Automatic Content-Aware Color and Tone Stylization
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 |
|---|---|---|---|
| Learn content-specific style rankings from a large photo collection instead of directly searching the curated style database | Automatic Content-Aware Color and Tone Stylization · 55-image benchmark, Study 1 | user rating: 3.169±0.444 -> 3.820±0.403 | Helped |
| Reduce the style database from 1500 exemplars to 50 (ablation) | Automatic Content-Aware Color and Tone Stylization · 55-image benchmark, Study 1 | user rating: 3.820±0.403 -> 3.620±0.413 | Hurt |
| Reduce the style database from 1500 exemplars to 50 | Direct semantic search · 55-image benchmark, Study 1 | user rating: 3.169±0.444 -> 2.421±0.436 | Hurt |
| Use regularized color and tone transfer rather than the compared statistics-based transfer methods | Automatic Content-Aware Color and Tone Stylization · 55-image benchmark, Study 2 | user rating: 3.730±0.440 -> 4.002±0.336 | Helped |
| Use multiple nearest semantic clusters and a style-distance threshold rather than simply taking top-ranked styles (ablation) | Automatic Content-Aware Color and Tone Stylization · Style sampling | style diversity | Helped |
| Increase the Fréchet-distance threshold during style sampling (ablation) | Automatic Content-Aware Color and Tone Stylization · Style sampling | style diversity | Helped |
| Increase the Fréchet-distance threshold during style sampling, allowing lower-ranked styles to be selected (ablation) | Automatic Content-Aware Color and Tone Stylization · Style sampling | visual artifacts | Hurt |
| Add regularization to the chrominance transfer function (ablation) | Automatic Content-Aware Color and Tone Stylization · Style transfer | visual artifacts | Helped |
| Use a smooth parametric luminance mapping instead of direct histogram matching (ablation) | Automatic Content-Aware Color and Tone Stylization · Style transfer | visual artifacts | Helped |
| Add face-specific luminance correction when a face is too dark (ablation) | Automatic Content-Aware Color and Tone Stylization · Portrait photographs | face exposure artifacts | Helped |
Closest papers by meaning
- A Content Transformation Block for Image Style Transfer (CVPR 2019 · similarity 0.89)
- Universal Style Transfer via Feature Transforms (NeurIPS 2017 · similarity 0.89)
- Conditional Balance: Improving Multi-Conditioning Trade-Offs in Image Generation (CVPR 2025 · similarity 0.86)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · similarity 0.86)
- OmniStyle: Filtering High Quality Style Transfer Data at Scale (CVPR 2025 · similarity 0.86)
- Free-Lunch Color-Texture Disentanglement for Stylized Image Generation (NeurIPS 2025 · similarity 0.86)
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.