DiffInk: Glyph- and Style-Aware Latent Diffusion Transformer for Text to Online Handwriting Generation
This work addresses inefficiencies and structural limitations in text-to-online handwriting generation for applications like digital writing or assistive technologies, representing a novel approach rather than an incremental improvement.
The paper tackled the problem of generating realistic full-line online handwriting from text and style references, proposing DiffInk, a latent diffusion Transformer framework that outperformed state-of-the-art methods in glyph accuracy and style fidelity while improving efficiency.
Deep generative models have advanced text-to-online handwriting generation (TOHG), which aims to synthesize realistic pen trajectories conditioned on textual input and style references. However, most existing methods still primarily focus on character- or word-level generation, resulting in inefficiency and a lack of holistic structural modeling when applied to full text lines. To address these issues, we propose DiffInk, the first latent diffusion Transformer framework for full-line handwriting generation. We first introduce InkVAE, a novel sequential variational autoencoder enhanced with two complementary latent-space regularization losses: (1) an OCR-based loss enforcing glyph-level accuracy, and (2) a style-classification loss preserving writing style. This dual regularization yields a semantically structured latent space where character content and writer styles are effectively disentangled. We then introduce InkDiT, a novel latent diffusion Transformer that integrates target text and reference styles to generate coherent pen trajectories. Experimental results demonstrate that DiffInk outperforms existing state-of-the-art methods in both glyph accuracy and style fidelity, while significantly improving generation efficiency. Code will be made publicly available.