Text2Grasp：基于物体抓取部位文本提示的抓取合成
Text2Grasp: Grasp synthesis by text prompts of object grasping parts
AI总结：
针对现有抓取合成方法中控制信号存在歧义的问题，提出Text2Grasp，通过物体抓取部位文本提示引导的两阶段扩散与优化方法，实现精确的部位级抓取控制及可比的抓取质量。
摘要：
手在人类抓取和操作物体的能力中发挥关键作用，可控的抓取合成是成功执行下游任务的关键。使用人类意图或任务级语言作为抓取控制信号的现有方法本质上面临歧义性。为应对这一挑战，我们提出一种由物体抓取部位文本提示引导的抓取合成方法Text2Grasp，它提供更精确的控制。具体而言，我们提出一种两阶段方法，包含一个文本引导的扩散模型TextGraspDiff，先生成粗略抓取姿态，再应用手与物体接触优化过程，以确保合理性与多样性。此外，通过利用大语言模型，我们的方法支持由任务级和个性化文本描述引导的抓取合成，无需额外人工标注。大量实验表明，我们的方法不仅实现了准确的部位级抓取控制，在抓取质量上也取得了可比的性能。
英文摘要：
The hand plays a pivotal role in human ability to grasp and manipulate objects and controllable grasp synthesis is the key for successfully performing downstream tasks. Existing methods that use human intention or task-level language as control signals for grasping inherently face ambiguity. To address this challenge, we propose a grasp synthesis method guided by text prompts of object grasping parts, Text2Grasp, which provides more precise control. Specifically, we present a two-stage method that includes a text-guided diffusion model TextGraspDiff to first generate a coarse grasp pose, then apply a hand-object contact optimization process to ensure both plausibility and diversity. Furthermore, by leveraging Large Language Model, our method facilitates grasp synthesis guided by task-level and personalized text descriptions without additional manual annotations. Extensive experiments demonstrate that our method achieves not only accurate part-level grasp control but also comparable performance in grasp quality.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
