Search papers, labs, and topics across Lattice.
This paper introduces a two-stage framework for handwriting trajectory recovery that first predicts ordered stroke instances before reconstructing the continuous motion within each stroke. By leveraging autoregressive ordered stroke prediction and incorporating direction-related structural cues, the method effectively addresses the inherent ambiguities in recovering dynamic writing processes from static images. Experiments reveal that this approach outperforms existing methods, achieving superior results in both Chinese handwriting and extending to English and Tamil scripts.
Recovering handwriting trajectories is significantly enhanced by predicting stroke order first, leading to better performance than traditional methods.
Handwriting trajectory recovery aims to infer the dynamic writing process hidden behind a static handwritten image. Since offline handwriting preserves only the final spatial ink pattern, temporal information such as stroke order, writing direction, and pen-tip motion is lost, making recovery inherently ambiguous. Existing learning-based methods often directly predict the complete character trajectory without explicitly exploiting the stroke-level organization of handwriting. We argue that recovering the writing process should follow the writing process itself. Accordingly, we propose a two-stage framework that first recovers ordered stroke instances and then reconstructs continuous within-stroke motion. The first stage integrates stroke extraction and stroke-order recovery through autoregressive ordered stroke prediction, while direction-related structural cues further support within-stroke trajectory generation. Experiments on Chinese handwriting show that the proposed ordered prediction is more effective than post-hoc stroke ordering. Even without trajectory simplification, our full-point model achieves numerically better results than those reported by all compared baselines, while a controlled analysis shows that trajectory sampling density substantially affects measured recovery performance. Additional experiments demonstrate generalization to unseen Chinese character categories and cross-language extensibility to English and Tamil handwriting.
