Research map / Image generation / Editing and style transfer
FontRL: Chinese Font Synthesis via Deep Reinforcement Learning
Read the paperCheck 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 |
|---|---|---|---|
| Use FontRL instead of SCFont | Chinese font synthesis · FZJHSXJW | L1 loss: 0.1173 -> 0.0855 | Helped |
| Use FontRL instead of SCFont | Chinese font synthesis · FZJHSXJW | IoU: 0.5459 -> 0.6963 | Helped |
| Use FontRL instead of SCFont | Chinese font synthesis · FZSSBJW | L1 loss: 0.1627 -> 0.1261 | Helped |
| Use FontRL instead of SCFont | Chinese font synthesis · FZSSBJW | IoU: 0.3163 -> 0.5399 | Helped |
| Use FontRL instead of SCFont | Chinese font synthesis · FZTLJW | L1 loss: 0.1188 -> 0.1074 | Helped |
| Use FontRL instead of SCFont | Chinese font synthesis · FZTLJW | IoU: 0.3574 -> 0.4836 | Helped |
| Use FontRL instead of SCFont | Chinese font synthesis · FZYNJW | L1 loss: 0.1245 -> 0.0966 | Helped |
| Use FontRL instead of SCFont | Chinese font synthesis · FZYNJW | IoU: 0.5442 -> 0.6890 | Helped |
| Use FontRL instead of SCFont | Chinese font synthesis · FZZJ-LPYBJW | L1 loss: 0.1191 -> 0.1035 | Helped |
| Use FontRL instead of SCFont | Chinese font synthesis · FZZJ-LPYBJW | IoU: 0.3197 -> 0.4843 | Helped |
| Increase maximum RL steps from 1 to 5 (ablation) | FontRL stroke modification · FZJHSXJW | average point distance: 0.310 -> 0.266 | Helped |
| Add BBoxNet to predict stroke positions and sizes (ablation) | FontRL · Chinese font synthesis | glyph detail quality | Helped |
Closest papers by meaning
- DeepCalliFont: Few-Shot Chinese Calligraphy Font Synthesis by Integrating Dual-Modality Generative Models (AAAI 2024 · similarity 0.89)
- Decoupling Layout from Glyph in Online Chinese Handwriting Generation (ICLR 2025 · similarity 0.88)
- VQ-FONT: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization (AAAI 2024 · similarity 0.87)
- IF-Font: Ideographic Description Sequence-Following Font Generation (NeurIPS 2024 · similarity 0.85)
- Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models (CVPR 2024 · similarity 0.84)
- VecGlypher: Unified Vector Glyph Generation with Language Models (CVPR 2026 · similarity 0.84)
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.