CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization

TL;DR

CONSTANT introduces a diffusion-based one-shot handwriting generation method that uses style-aware quantization and patch contrastive learning to produce realistic, diverse, and style-adaptive handwritten images across multiple languages.

Contribution

The paper proposes a novel diffusion model with style-aware quantization and contrastive objectives for high-quality, one-shot handwriting generation, addressing previous limitations in style diversity and local detail preservation.

Findings

Outperforms state-of-the-art methods on multiple language datasets.

Effectively captures diverse writer styles with high visual quality.

Demonstrates strong generalization to unseen styles and languages.

Abstract

One-shot styled handwriting image generation, despite achieving impressive results in recent years, remains challenging due to the difficulty in capturing the intricate and diverse characteristics of human handwriting by using solely a single reference image. Existing methods still struggle to generate visually appealing and realistic handwritten images and adapt to complex, unseen writer styles, struggling to isolate invariant style features (e.g., slant, stroke width, curvature) while ignoring irrelevant noise. To tackle this problem, we introduce Patch Contrastive Enhancement and Style-Aware Quantization via Denoising Diffusion (CONSTANT), a novel one-shot handwriting generation via diffusion model. CONSTANT leverages three key innovations: 1) a Style-Aware Quantization (SAQ) module that models style as discrete visual tokens capturing distinct concepts; 2) a contrastive objective to ensure these tokens are well-separated and meaningful in the embedding style space; 3) a latent patch-based contrastive (LLatentPCE) objective help improving quality and local structures by aligning multiscale spatial patches of generated and real features in latent space. Extensive experiments and analysis on benchmark datasets from multiple languages, including English, Chinese, and our proposed ViHTGen dataset for Vietnamese, demonstrate the superiority of adapting to new reference styles and producing highly detailed images of our method over state-of-the-art approaches. Code is available at GitHub