MaskDexGrasp：面向部件感知灵巧抓取合成的生成式掩码建模
MaskDexGrasp: Generative Masked Modeling for Part-Aware Dexterous Grasp Synthesis
把高维灵巧手抓取姿态离散化为部件级 token 并用双向掩码 Transformer 生成，这种「分词器 + 掩码建模」的范式可直接迁移到人手/手物交互姿态合成与部件级可控编辑任务。
原文依据 a bidirectional masked grasp transformer is then developed to predict grasp tokens conditioned on object geometry and task description
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论灵巧抓取生成是使机器人能够完成人类级别操作的一项核心任务。然而，灵巧手始终具有高维自由度与驱动空间，使得依赖整体潜变量表示的现有方法难以生成高质量且语义对齐的抓取。本文提出 MaskDexGrasp 以应对这些挑战。我们首先提出一种部件感知的抓取分词器，将灵巧抓取分解为离散 token，从而便于对解剖学依赖关系进行组合式建模。在此表示的基础上，我们进一步设计了一种双向掩码抓取 Transformer，以物体几何与任务描述为条件预测抓取 token，在保证抓取生成连贯性的同时支持细粒度的部件级编辑。为便于评测，我们构建了一个灵巧抓取数据集，包含 65K 个抓取实例与 260K 条覆盖 11 类任务的丰富标注描述。大量实验表明，我们的方法取得了最优性能。项目主页见 https://binghui-z.github.io/MaskDexGrasp/。
英文原文摘要 1146 字符
Dexterous grasp generation is a predominant task that enables robots to perform human-level manipulation. However, a dexterous hand always maintains high-dimensional DoF and actuation space, making existing approaches that rely on holistic latent representations difficult to produce high-quality and semantically aligned grasps. In this paper, we propose MaskDexGrasp to address these challenges. We first present a part-aware grasp tokenizer that decomposes dexterous grasps into discrete tokens, facilitating compositional modeling of anatomical dependencies. Building upon this representation, a bidirectional masked grasp transformer is then developed to predict grasp tokens conditioned on object geometry and task description, ensuring coherent grasp generation while allowing fine-grained part-level editing. To facilitate evaluation, we construct a dexterous grasp dataset that comprises 65K grasping instances and 260K richly annotated descriptions covering 11 tasks. Comprehensive experiments demonstrate that our method achieves the state-of-the-art performance. Project page is available at https://binghui-z.github.io/MaskDexGrasp/.