面向类人机器人书写的轮廓感知生成
Towards Human-Like Robot Handwriting via Contour-Aware Generation
将字符笔画轮廓建模为图结构并用GNN联合编码局部笔画细节与全局字形结构，这一「轮廓感知图表示」思路可迁移到笔迹/线条类视觉任务（如草图生成、矢量字体合成、手写识别中的结构先验建模）。
原文依据 we propose Graph-based Handwriting Trajectory Reconstruction (G-HTR), a novel method using contour-aware graphs to jointly model stroke contour and character structure
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论让机器模拟人类手写是一个有前景的研究方向。然而，现有方法大多主要关注复现书写轨迹以捕捉整体字符结构，而忽略了笔画轮廓建模这一关键方面。因此，这些方法难以生成视觉上真实、类人的手写，限制了其在书法机器人等场景中的适用性。为解决这一问题，我们提出了一个新任务，称为轮廓感知手写轨迹重建（CHTR）。该任务面临两大挑战：1）现有手写数据集缺乏笔画轮廓标注，使监督学习难以进行；2）以往方法无法在恢复笔画轮廓的同时保持整体字符结构。针对数据集限制，我们提出了 CHTR-110K，一个带有精细笔画轮廓标注的大规模字符数据集。针对技术挑战，我们提出了基于图的手写轨迹重建方法（G-HTR），这是一种利用轮廓感知图联合建模笔画轮廓与字符结构的新方法。我们使用图神经网络捕捉节点间的结构关系，并引入多尺度图学习策略以同时编码细粒度笔画细节与全局字符结构。大量实验验证了 G-HTR 的有效性，在我们提出的 CHTR-110K 以及广泛使用的 CASIA-OLHWDB 数据集上均优于以往的最优方法。G-HTR 在部署到机器人上时还展现出良好的真实世界效果，证实了其实用价值。为支持未来研究，我们将公开源代码与数据集。
英文原文摘要 1691 字符
Empowering machines to simulate human handwriting is a promising research direction. Most existing methods, however, primarily focus on reproducing the writing trajectory to capture the overall character structure, while neglecting the critical aspect of stroke contour modeling. Consequently, these methods struggle to generate visually realistic, human-like handwriting, limiting their applicability in scenarios such as calligraphy robots. To address this issue, we propose a new task, called Contour-aware Handwriting Trajectory Reconstruction (CHTR). This task presents two major challenges: 1) Existing handwriting datasets lack stroke contour annotations, making supervised learning difficult; 2) Previous methods are unable to recover stroke contour and preserve the overall character structure jointly. To address the dataset limitation, we present CHTR-110K, a large-scale character dataset with refined stroke contour annotations. To tackle the technical challenge, we propose Graph-based Handwriting Trajectory Reconstruction (G-HTR), a novel method using contour-aware graphs to jointly model stroke contour and character structure. We use a Graph Neural Network to capture structural relationships among nodes and introduce a multi-scale graph learning strategy to encode both fine-grained stroke details and global character structure. Extensive experiments verify the effectiveness of G-HTR, outperforming previous state-of-the-art methods on both our CHTR-110K and the widely-used CASIA-OLHWDB dataset. G-HTR further shows strong real-world results when deployed on robots, confirming its practical value. To support future research, we will release source code and dataset.