Research map / Image generation / Editing and style transfer
Diverse Image Style Transfer via Invertible Cross-Space Mapping
Haibo Chen, Lei Zhao, Huiming Zhang, Zhizhong Wang, Zhiwen Zuo, Ailin Li, Wei Xing, Dongming Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 the disentanglement branch (style encoder with content encoder) (ablation) | DIST · Wikiart/Places365 | deception rate: 0.112 -> 0.525 | Improved |
| add the disentanglement branch (ablation) | DIST · Wikiart/Places365 | LPIPS diversity: 0.446 -> 0.464 | No clear effect |
| add the inverse branch (invert style to noise vector) (ablation) | DIST · Wikiart/Places365 | LPIPS diversity: 0.034 -> 0.464 | Improved |
| add the inverse branch (ablation) | DIST · Wikiart/Places365 | deception rate: 0.531 -> 0.525 | No clear effect |
| use DIST with inverse branch instead of deterministic AST | AST · Wikiart/Places365 | LPIPS diversity: 0.000 -> 0.464 | Improved |
| use DIST instead of AST in quality | AST · Wikiart/Places365 | deception rate: 0.454 -> 0.525 | Improved |
| use DIST instead of DFP for diversity-oriented stylization | DFP · Wikiart/Places365 | deception rate: 0.027 -> 0.525 | Improved |
| use DIST instead of MUNIT | MUNIT · Wikiart/Places365 | LPIPS diversity: 0.538 -> 0.464 | Hurt |
| use DIST instead of MUNIT | MUNIT · Wikiart/Places365 | deception rate: 0.121 -> 0.525 | Improved |
Closest papers by meaning
- ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank (AAAI 2024 · similarity 0.88)
- HSI: A Holistic Style Injector for Arbitrary Style Transfer (CVPR 2025 · similarity 0.87)
- Z*: Zero-shot Style Transfer via Attention Reweighting (CVPR 2024 · similarity 0.87)
- Free-Lunch Color-Texture Disentanglement for Stylized Image Generation (NeurIPS 2025 · similarity 0.87)
- OmniStyle: Filtering High Quality Style Transfer Data at Scale (CVPR 2025 · similarity 0.86)
- StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer (CVPR 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.
