Skeleton and Font Generation Network for Zero-shot Chinese Character Generation

2025-01-14

AI Summary

To address the challenge of low-fidelity reconstruction of rare and misspelled Chinese characters in zero-shot font generation, this paper proposes a radical glyph-root-level content-style alignment paradigm. First, we design a lightweight skeleton construction module that operates without content image input, enabling resource-efficient, text-driven structural modeling. Second, we introduce a glyph-root-granular feature disentanglement and alignment generator to mitigate character distortion caused by training bias. Third, we pioneer the integration of misspelled character generation into Chinese character error correction pedagogy, facilitating interpretable, correction-aware augmentation. Experiments demonstrate that our method significantly outperforms state-of-the-art approaches on zero-shot font generation. Moreover, incorporating generated misspelled characters improves downstream correction model accuracy by +4.2%, validating both its theoretical novelty and educational applicability.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Automatic font generation remains a challenging research issue, primarily due to the vast number of Chinese characters, each with unique and intricate structures. Our investigation of previous studies reveals inherent bias capable of causing structural changes in characters. Specifically, when generating a Chinese character similar to, but different from, those in the training samples, the bias is prone to either correcting or ignoring these subtle variations. To address this concern, we propose a novel Skeleton and Font Generation Network (SFGN) to achieve a more robust Chinese character font generation. Our approach includes a skeleton builder and font generator. The skeleton builder synthesizes content features using low-resource text input, enabling our technique to realize font generation independently of content image inputs. Unlike previous font generation methods that treat font style as a global embedding, we introduce a font generator to align content and style features on the radical level, which is a brand-new perspective for font generation. Except for common characters, we also conduct experiments on misspelled characters, a substantial portion of which slightly differs from the common ones. Our approach visually demonstrates the efficacy of generated images and outperforms current state-of-the-art font generation methods. Moreover, we believe that misspelled character generation have significant pedagogical implications and verify such supposition through experiments. We used generated misspelled characters as data augmentation in Chinese character error correction tasks, simulating the scenario where students learn handwritten Chinese characters with the help of misspelled characters. The significantly improved performance of error correction tasks demonstrates the effectiveness of our proposed approach and the value of misspelled character generation.

Problem

• Chinese character generation
• typographical errors
• detail preservation

Innovation

• SFGN
• Skeleton Generation
• Glyph Generation