Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation
Authors:
Preprint
Abstract
Manual font design is an intricate process that transforms a stylistic visual concept into a coherent glyph set. This challenge persists in automated Few-shot Font Generation (FFG), where models often struggle to preserve both the structural integrity and stylistic fidelity from limited references. While autoregressive (AR) models have demonstrated impressive generative capabilities, their application to FFG is constrained by conventional patch-level tokenization, which neglects global dependencies crucial for coherent font synthesis. Moreover, existing FFG methods remain within the image-to-image paradigm, relying solely on visual references and overlooking the role of language in conveying stylistic intent during font design. To address these limitations, we propose GAR-Font, a novel AR framework for multimodal few-shot font generation. GAR-Font introduces a global-aware tokenizer that effectively captures both local structures and global stylistic patterns, a multimodal style encoder offering flexible style control through a lightweight language-style adapter without requiring intensive multimodal pretraining, and a post-refinement pipeline that further enhances structural fidelity and style coherence. Extensive experiments show that GAR-Font outperforms existing FFG methods, excelling in maintaining global style faithfulness and achieving higher-quality results with textual stylistic guidance.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- HFH-Font: Few-shot Chinese Font Synthesis with Higher Quality, Faster Speed, and Higher ResolutionACM Transactions on Graphics, 2024
- Diff-Font: Diffusion Model for Robust One-Shot Font GenerationInternational Journal of Computer Vision, 2024
- TextAdapter: Self-Supervised Domain Adaptation for Cross-Domain Text RecognitionIEEE Transactions on Multimedia, 2024
- Few-Shot Font Generation by Learning Style Difference and SimilarityIEEE Transactions on Circuits and Systems for Video Technology, 2024
- An Image is Worth 32 Tokens for Reconstruction and Generation2024
- Video-LLaVA: Learning United Visual Representation by Alignment Before Projection2024
- Flamingo: A Visual Language Model for Few-Shot Learning2022
- Artistic glyph image synthesis via one-stage few-shot learningACM Transactions on Graphics, 2019
- FontRNN: Generating Large‐scale Chinese Fonts via Recurrent Neural NetworkComputer Graphics Forum, 2019