DNA: Dual-branch Network with Adaptation for Open-Set Online Handwriting Generation

TL;DR

This paper introduces DNA, a dual-branch network with adaptation, to generate realistic online handwriting for unseen characters, improving the diversity and realism of synthetic handwriting in open-set scenarios.

Contribution

The paper proposes a novel dual-branch network with adaptation for open-set online handwriting generation, effectively handling unseen characters and styles.

Findings

Achieves state-of-the-art performance on unseen handwriting generation tasks.

Effectively decomposes character content into structural and texture features.

Demonstrates realistic and diverse handwriting synthesis for unseen characters.

Abstract

Online handwriting generation (OHG) enhances handwriting recognition models by synthesizing diverse, human-like samples. However, existing OHG methods struggle to generate unseen characters, particularly in glyph-based languages like Chinese, limiting their real-world applicability. In this paper, we introduce our method for OHG, where the writer's style and the characters generated during testing are unseen during training. To tackle this challenge, we propose a Dual-branch Network with Adaptation (DNA), which comprises an adaptive style branch and an adaptive content branch. The style branch learns stroke attributes such as writing direction, spacing, placement, and flow to generate realistic handwriting. Meanwhile, the content branch is designed to generalize effectively to unseen characters by decomposing character content into structural information and texture details, extracted via local and global encoders, respectively. Extensive experiments demonstrate that our DNA model is well-suited for the unseen OHG setting, achieving state-of-the-art performance.