具有完整抓取分类体系与动力学的密集手-物（HO）GraspNet
Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamics
AI总结：
本文构建覆盖完整抓取分类、多样物体与手形的真实三维手-物交互数据集 HOGraspNet，并通过抓取分类和手部姿态估计验证其价值。
摘要：
现有的三维手-物交互数据集在数据规模、交互场景的数据多样性或标注质量方面均存在局限。本文提出一个全面的手-物交互训练新数据集 HOGraspNet。它是唯一捕捉完整抓取分类体系的真实数据集，提供抓取标注和广泛的类内变化。将抓取分类作为原子动作，其空间与时间组合可表示围绕物体的复杂手部活动。我们依据形状和尺寸分类，从 YCB 数据集中选取22个刚性物体，并选取另外8个复合物体，确保覆盖所有手部抓取构型。该数据集包含来自99名年龄在10至74岁参与者的多样手形、连续视频帧，以及150万帧带标注的稀疏 RGB-Depth 帧。它提供三维手部与物体网格、三维关键点、接触图以及“抓取标签”。准确的手部和物体三维网格通过将手部参数化模型（MANO）和手部隐式函数（HALO）拟合到多视角 RGBD 帧获得，而 MoCap 系统仅用于物体。需要注意的是，HALO 拟合无需任何参数调优，因此可扩展到数据集规模，并达到与 MANO 相当的精度。我们在相关任务上评估 HOGraspNet：抓取分类和三维手部姿态估计。结果显示，性能会随抓取类型和物体类别而变化，表明本数据集所捕捉交互空间的潜在重要性。所提供的数据旨在学习三维手-物交互的通用形状先验或基础模型。我们的数据集和代码可在 https://hograspnet2024.github.io/ 获取。
英文摘要：
Existing datasets for 3D hand-object interaction are limited either in the data cardinality, data variations in interaction scenarios, or the quality of annotations. In this work, we present a comprehensive new training dataset for hand-object interaction called HOGraspNet. It is the only real dataset that captures full grasp taxonomies, providing grasp annotation and wide intraclass variations. Using grasp taxonomies as atomic actions, their space and time combinatorial can represent complex hand activities around objects. We select 22 rigid objects from the YCB dataset and 8 other compound objects using shape and size taxonomies, ensuring coverage of all hand grasp configurations. The dataset includes diverse hand shapes from 99 participants aged 10 to 74, continuous video frames, and a 1.5M RGB-Depth of sparse frames with annotations. It offers labels for 3D hand and object meshes, 3D keypoints, contact maps, and \emph{grasp labels}. Accurate hand and object 3D meshes are obtained by fitting the hand parametric model (MANO) and the hand implicit function (HALO) to multi-view RGBD frames, with the MoCap system only for objects. Note that HALO fitting does not require any parameter tuning, enabling scalability to the dataset's size with comparable accuracy to MANO. We evaluate HOGraspNet on relevant tasks: grasp classification and 3D hand pose estimation. The result shows performance variations based on grasp type and object class, indicating the potential importance of the interaction space captured by our dataset. The provided data aims at learning universal shape priors or foundation models for 3D hand-object interaction. Our dataset and code are available at https://hograspnet2024.github.io/.
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。
