Research map / Image generation / Editing and style transfer
Domain-Specific Mappings for Generative Adversarial Style Transfer
Hsin-Yu Chang, Zhixiang Wang, Yung-Yu Chuang
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 domain-specific content mapping to MUNIT-style disentangled translation | Ours · Cat to Dog | FID: 38.09 -> 13.60 | Improved |
| add domain-specific content mapping (vs MUNIT) | Ours · Photograph to Portrait | FID: 89.97 -> 45.81 | Improved |
| add domain-specific content mapping (vs MUNIT) | Ours · Average over 6 tasks | FID: 70.69 -> 47.85 | Improved |
| use Ours instead of MSGAN | Ours · Average over 6 tasks | FID: 55.18 -> 47.85 | Improved |
| use Ours instead of MSGAN | Ours · Portrait to Photograph | FID: 57.07 -> 62.44 | Hurt |
| use Ours instead of MSGAN | Ours · Cat to Dog | LPIPS: 0.5051 -> 0.4149 | Hurt |
| use Ours instead of MSGAN | Ours · Photograph to Portrait | LPIPS: 0.2917 -> 0.3699 | Improved |
| use Ours instead of MSGAN | Ours · Average over 6 tasks | LPIPS: 0.3978 -> 0.3980 | No clear effect |
| add domain-specific content mapping (ablation) | Ours · Dog to Cat ablation (qualitative) | layout preservation | Improved |
| add L1 dsc reconstruction loss (ablation) | Ours · Dog to Cat ablation (qualitative) | mapping learning | Improved |
| add domain invariant content loss L1 dic (ablation) | Ours · Dog to Cat ablation (qualitative) | content preservation stability | Improved |
Closest papers by meaning
- A Geometrical Perspective on Image Style Transfer with Adversarial Learning (TPAMI 2020 · similarity 0.89)
- Domain-Aware Universal Style Transfer (ICCV 2021 · similarity 0.89)
- Generalized One-shot Domain Adaptation of Generative Adversarial Networks (NeurIPS 2022 · similarity 0.88)
- In the Light of Feature Distributions: Moment Matching for Neural Style Transfer (CVPR 2021 · similarity 0.88)
- Domain Generalizable Portrait Style Transfer (ICCV 2025 · similarity 0.88)
- Universal Style Transfer via Feature Transforms (NeurIPS 2017 · similarity 0.87)
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.
