arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.04560cs.CV
收藏

联合扩散用于通用手-物体抓取生成

Joint Diffusion for Universal Hand-Object Grasp Generation

Carnegie Mellon University(卡内基梅隆大学);Adobe(Adobe公司);Roblox(Roblox公司)

Jinkun Cao, Jingyuan Liu, Kris Kitani, Yi Zhou

AI总结:

本文提出联合手-物体扩散模型,通过统一潜在表示生成手和物体的抓取,利用大规模物体数据提升通用性,实现无条件和条件抓取生成。

摘要:

预测和生成人类手部对物体的抓取对于动画和机器人任务至关重要。在本工作中,我们关注通过单一扩散模型生成手和物体的抓取。我们提出的联合手-物体扩散(JHOD)模型在统一的潜在表示中建模手和物体。它利用手-物体抓取数据来学习使手和物体形成合理抓取的方法。此外,为了确保在多样化的物体形状上具有通用性,它利用大规模物体数据集来学习包容性的物体潜在嵌入。无论是否给定物体作为可选条件,扩散模型都可以生成无条件或针对物体的抓取。与通常仅从手-物体抓取数据学习物体条件抓取生成的方法相比,我们的方法受益于更多样化的物体数据用于训练,以更普遍地处理抓取生成。根据定性和定量实验,条件和无条件生成的手抓取都实现了良好的视觉合理性与多样性。通过从大规模物体数据集中学习的额外包容性物体表示,所提出的方法能够很好地推广到未见过的物体形状。

英文摘要:

Predicting and generating human hand grasp over objects is critical for animation and robotic tasks. In this work, we focus on generating both the hand and objects in a grasp by a single diffusion model. Our proposed Joint Hand-Object Diffusion (JHOD) models the hand and object in a unified latent representation. It uses the hand-object grasping data to learn to accommodate hand and object to form plausible grasps. Also, to enforce the generalizability over diverse object shapes, it leverages large-scale object datasets to learn an inclusive object latent embedding. With or without a given object as an optional condition, the diffusion model can generate grasps unconditionally or conditional to the object. Compared to the usual practice of learning object-conditioned grasp generation from only hand-object grasp data, our method benefits from more diverse object data used for training to handle grasp generation more universally. According to both qualitative and quantitative experiments, both conditional and unconditional generation of hand grasp achieves good visual plausibility and diversity. With the extra inclusiveness of object representation learned from large-scale object datasets, the proposed method generalizes well to unseen object shapes.

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。

↑