Research map / Graph learning / GNN architectures
Learning Graph Neural Networks for Image Style Transfer
Yongcheng Jing, Yining Mao, Yiding Yang, Yibing Zhan, Mingli Song, Xinchao Wang, Dacheng Tao
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 |
|---|---|---|---|
| use GAT attention aggregation instead of GCN, GIN, EdgeConv or GraphSage (ablation) | GNN style transfer · arbitrary style transfer (qualitative) | stylization quality | Improved |
| add deformable scale prediction for style patches (ablation) | GNN style transfer · arbitrary style transfer (qualitative) | stylization quality | Improved |
| add content-content intra-domain edges (ablation) | GNN style transfer · arbitrary style transfer (qualitative) | stylization quality | Improved |
| use normalized cross-correlation instead of Euclidean distance for KNN (ablation) | GNN style transfer · arbitrary style transfer (qualitative) | stylization quality | Improved |
| increase patch size (ablation) | GNN style transfer · arbitrary style transfer (qualitative) | stroke size | Mixed |
| increase number of connections k at inference (ablation) | GNN style transfer · arbitrary style transfer (qualitative) | stylization diversity | Mixed |
Closest papers by meaning
- Multimodal Style Transfer via Graph Cuts (ICCV 2019 · similarity 0.91)
- Separating Style and Content for Generalized Style Transfer (CVPR 2018 · similarity 0.89)
- Rethinking and Improving the Robustness of Image Style Transfer (CVPR 2021 · similarity 0.88)
- Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network (CVPR 2024 · similarity 0.88)
- Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer (CVPR 2024 · similarity 0.87)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · 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.
