Research map / Image generation / Editing and style transfer
Few-shot Compositional Font Generation with Dual Memory
Junbum Cha, Sanghyuk Chun, Gayoung Lee, Bado Lee, Seonghyeon Kim, Hwalsuk Lee
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 dynamic memory (ablation) | FUNIT-like baseline · Korean-handwriting | style accuracy | Improved |
| add persistent memory (ablation) | FUNIT-like baseline · Korean-handwriting | style accuracy | Improved |
| add compositional generator (self-attention encoder, hourglass decoder) (ablation) | DM-Font with memories · Korean-handwriting | accuracy | Improved |
| add component-classification loss (ablation) | DM-Font · Korean-handwriting | accuracy | Improved |
| add L1 loss (ablation) | DM-Font · Korean-handwriting | accuracy | Improved |
| add feature matching loss (ablation) | DM-Font · Korean-handwriting | accuracy | Improved |
| evaluate AGIS-Net on unseen instead of seen characters | AGIS-Net · Korean-handwriting | content accuracy: 98.7 -> 98.3 | Hurt |
| evaluate AGIS-Net on unseen instead of seen characters | AGIS-Net · Korean-handwriting | mFID: 23.9 -> 25.9 | Hurt |
| use DM-Font instead of baseline few-shot methods | DM-Font · Korean-handwriting (unseen) | style-aware accuracy: about 5% -> 62.6% | Improved |
Closest papers by meaning
- VQ-FONT: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization (AAAI 2024 · similarity 0.89)
- IF-Font: Ideographic Description Sequence-Following Font Generation (NeurIPS 2024 · similarity 0.88)
- DeepCalliFont: Few-Shot Chinese Calligraphy Font Synthesis by Integrating Dual-Modality Generative Models (AAAI 2024 · similarity 0.88)
- VecGlypher: Unified Vector Glyph Generation with Language Models (CVPR 2026 · similarity 0.87)
- Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models (CVPR 2024 · similarity 0.87)
- Decoupling Layout from Glyph in Online Chinese Handwriting Generation (ICLR 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.
