Research map / Image generation / Editing and style transfer
Deep Photo 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 locally affine photorealism regularization | Neural Style · photographic style transfer | photorealism | Helped |
| add semantic segmentation guidance to the style loss | Deep Photo Style Transfer · photographic style transfer with differing scene content | semantic accuracy | Helped |
| use locally varying color transformations rather than a global color mapping | global color transfer methods · style transfer requiring spatially varying changes | style faithfulness | Helped |
| use Deep Photo Style Transfer instead of global methods | style transfer user study · style transfer user study | style preference: more than 80% | Helped |
| set photorealism regularization too low (ablation) | Deep Photo Style Transfer · photographic style transfer | photorealism | Hurt |
| set photorealism regularization too high (ablation) | Deep Photo Style Transfer · photographic style transfer | style faithfulness | Hurt |
| optimize the full objective directly instead of using two-stage optimization (ablation) | Deep Photo Style Transfer · photographic style transfer | local color transfer | Hurt |
| retain fine-grained semantic classes instead of merging similar classes (ablation) | semantic segmentation guidance · photographic style transfer | output quality | Hurt |
Closest papers by meaning
- Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer (CVPR 2017 · similarity 0.91)
- Deep Translation Prior: Test-Time Training for Photorealistic Style Transfer (AAAI 2022 · similarity 0.90)
- A Flexible Convolutional Solver for Fast Style Transfers (CVPR 2019 · similarity 0.90)
- ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank (AAAI 2024 · similarity 0.86)
- Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer (CVPR 2024 · similarity 0.86)
- FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields (AAAI 2024 · 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.
