Abstract
In this paper, we propose TrInk, a Transformer-based model for ink generation, which effectively captures global dependencies. To better facilitate the alignment between the input text and generated stroke points, we introduce scaled positional embeddings and a Gaussian memory mask in the cross-attention module. Additionally, we design both subjective and objective evaluation pipelines to comprehensively assess the legibility and style consistency of the generated handwriting. Experiments demonstrate that our Transformer-based model achieves a 35.56\% reduction in character error rate (CER) and an 29.66% reduction in word error rate (WER) on the IAM-OnDB dataset compared to previous methods. We provide an demo page with handwriting samples from TrInk and baseline models at: this https URL
Abstract (translated)
在这篇论文中，我们提出了TrInk，这是一种基于Transformer的墨迹生成模型，能够有效捕捉全局依赖关系。为了更好地促进输入文本和生成笔画点之间的对齐，我们在跨注意力模块中引入了缩放位置嵌入和高斯记忆掩码。此外，我们还设计了主观和客观评估管道，以全面评估所生成手写体的可读性和风格一致性。实验表明，在IAM-OnDB数据集上，我们的基于Transformer的模型相比先前的方法将字符错误率（CER）降低了35.56%，将单词错误率（WER）降低了29.66%。我们提供了一个演示页面，其中包含TrInk和基线模型的手写样本：[此处应为URL链接]
URL
https://arxiv.org/abs/2508.21098
