Research map / Image generation / Editing and style transfer
CF-Font: Content Fusion for Few-Shot Font Generation
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 |
|---|---|---|---|
| Add PC-WDL to DGN (ablation) | DGN · Seen Fonts | L1: 0.06251 -> 0.06261 | No clear effect |
| Add PC-WDL to DGN (ablation) | DGN · Unseen Fonts | L1: 0.07841 -> 0.07803 | Helped |
| Add CFM to DGN + PC-WDL (ablation) | DGN + PC-WDL · Unseen Fonts | L1: 0.07803 -> 0.07574 | Helped |
| Add CFM to DGN + PC-WDL (ablation) | DGN + PC-WDL · Unseen Fonts | FID: 26.79 -> 27.01 | No clear effect |
| Add ISR to DGN + PC-WDL + CFM (ablation) | DGN + PC-WDL + CFM · Unseen Fonts | L1: 0.07574 -> 0.07394 | Helped |
| Replace content fusion with closest basis-font retrieval (ablation) | DGN + PC-WDL · Unseen Fonts | L1: 0.07803 -> 0.08009 | Hurt |
| Replace content fusion with closest-font retrieval from training set (ablation) | DGN + PC-WDL · Unseen Fonts | FID: 26.79 -> 34.83 | Hurt |
| Use PC-KL rather than the baseline reconstruction loss (ablation) | Baseline · Unseen Fonts | LPIPS: 0.1198 -> 0.1191 | Helped |
| Use PC-WDL rather than the baseline reconstruction loss (ablation) | Baseline · Unseen Fonts | FID: 27.98 -> 26.79 | Helped |
| Use CFM, PC-WDL, and ISR | DG-Font · Unseen Fonts | L1: 0.07841 -> 0.07394 | Helped |
Closest papers by meaning
- Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models (CVPR 2024 · similarity 0.88)
- FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning (AAAI 2024 · 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 0.86)
- VecFusion: Vector Font Generation with Diffusion (CVPR 2024 · similarity 0.83)
- DeepCalliFont: Few-Shot Chinese Calligraphy Font Synthesis by Integrating Dual-Modality Generative Models (AAAI 2024 · similarity 0.83)
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.