Research map / Image generation / Editing and style transfer
Multi-Content GAN for Few-Shot Font Style Transfer
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 end-to-end MC-GAN instead of patch-based text effect transfer on GlyphNet-generated glyphs | ornamented glyph style transfer · 33 web font examples | user preference: 80.0% | Helped |
| Pre-train OrnaNet on gradient-based ornamentations rather than randomly initialize it (ablation) | MC-GAN · ornamented glyph style transfer | generated result quality | No clear effect |
| Add the weighted L1 regularizer that keeps GlyphNet predictions near the pre-trained GlyphNet predictions (ablation) | MC-GAN · end-to-end ornamented glyph synthesis | style transfer quality | Mixed |
| Remove the weighted L1 regularizer on GlyphNet (ablation) | MC-GAN · end-to-end ornamented glyph synthesis | style transfer quality | Mixed |
| Add the MSE regularizer on generated grayscale glyph masks (ablation) | MC-GAN · end-to-end ornamented glyph synthesis | grayscale glyph quality | Helped |
| Add the MSE regularizer on generated color glyph masks (ablation) | MC-GAN · end-to-end ornamented glyph synthesis | color glyph quality | Helped |
| Use all proposed loss terms (ablation) | MC-GAN · end-to-end ornamented glyph synthesis | generated result quality | Helped |
| Increase the number of observed glyphs | pre-trained GlyphNet · 1500-font subset | SSIM | Helped |
Closest papers by meaning
- Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models (CVPR 2024 · similarity 0.89)
- FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning (AAAI 2024 · similarity 0.87)
- VQ-FONT: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization (AAAI 2024 · similarity 0.86)
- VecGlypher: Unified Vector Glyph Generation with Language Models (CVPR 2026 · similarity 0.86)
- IF-Font: Ideographic Description Sequence-Following Font Generation (NeurIPS 2024 · similarity 0.86)
- CSGO: Content-Style Composition in Text-to-Image Generation (NeurIPS 2025 · similarity 0.85)
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.