InkDiffuser: High-Fidelity One-shot Chinese Calligraphy via Differentiable Morphological Optimization

2026-05-07

AI Summary

Existing methods for Chinese calligraphy generation often suffer from poor stroke rendering quality and distorted ink appearance, leading to insufficient visual fidelity and artistic fluency. This work proposes InkDiffuser, a diffusion-based single-sample Chinese calligraphy generation framework that introduces a novel differentiable ink structure (DIS) loss. By integrating differentiable morphological operations into the diffusion process and incorporating a high-frequency feature enhancement mechanism, InkDiffuser accurately reconstructs both character structure and ink texture details. Experimental results demonstrate that the proposed method significantly outperforms existing few-shot font generation approaches across diverse calligraphic styles and complex characters, achieving notable improvements in structural consistency, detail fidelity, and visual realism.

Abstract

Current Chinese calligraphy generation methods suffer from poor stroke rendering and unrealistic ink morphology, resulting in outputs with limited visual fidelity and artistic fluidity. To address this problem, we propose \textbf{InkDiffuser}, a diffusion-based generative framework for one-shot Chinese calligraphy synthesis. To guarantee high-fidelity rendering, we introduce two core contributions: a high-frequency enhancement mechanism and a Differentiable Ink Structure (DIS) loss that explicitly regularizes ink morphology. Inspired by the observation that high-frequency information in individual samples typically carries contour details, we enhance content extraction by explicitly fusing high-frequency representations for more accurate font structure. Furthermore, we propose a differentiable ink structure loss that integrates differentiable morphological operations into the diffusion process. By allowing the model to learn an explicit decomposition of ink-trace structures, DIS facilitates fine-grained refinement of stroke contours and delivers significantly improved visual realism in the generated calligraphy. Extensive experiments on various calligraphic styles and complex characters demonstrate that InkDiffuser can generate superior calligraphy fonts with realistic ink rendering effects from only a single reference glyph and outperform existing few-shot font generation approaches in structural consistency, detail fidelity, and visual authenticity. The code is available at the following address: https://github.com/JingVIPLab/InkDiffuser.

Problem

• Chinese calligraphy generation
• stroke rendering
• ink morphology
• visual fidelity
• artistic fluidity

Innovation

• diffusion model
• differentiable morphology
• ink structure
• high-frequency enhancement
• one-shot calligraphy generation