InterMASH：用于抓取合成的统一几何表示
InterMASH: A Unified Geometric Representation for Grasp Synthesis
浏览论文内容
中文总结 AI 辅助
InterMASH提出一种基于球面锚点和球谐函数的统一几何表示，并采用条件扩散Transformer联合生成手部几何与接触，在ShadowHand基准上达到先进性能，且跨具身微调可提升机器人抓取成功率与多样性。
中文摘要 AI 辅助
抓取合成旨在生成稳定且物理上合理的手-物体交互，已成为人手建模和机器人操作中的基本问题。然而，由于手部形态和表面建模的差异，目前仍缺乏一种跨人手和机器人手的统一表示。先前的方法通常依赖接触图或密集隐式描述符来表示交互，但这些表示往往不完整，或计算成本高且冗余。我们提出了InterMASH，一种利用球面固定锚点建立跨具身对应的统一几何表示。在每个锚点处，低阶球谐函数紧凑地编码局部手部几何、物体几何和接触，形成显式且可解释的标记序列。基于这种原生标记化结构，我们引入了一个条件扩散Transformer，直接在所提出的InterMASH表示空间中操作，并联合生成手部几何和接触，从而提高一致性和物理合理性。我们的方法在大规模ShadowHand基准测试中，在关键物理可行性指标上达到了与最先进方法相当的性能，支持多只手的联合训练，并表明利用人类抓取数据进行跨具身微调可以提高机器人抓取的成功率和多样性。项目页面可在该https URL获取。
英文摘要
Grasp synthesis aims to generate stable and physically plausible hand--object interactions, and has become a fundamental problem in both human hand modeling and robotic manipulation. However, a unified representation across human and robotic hands is still lacking, mainly due to differences in hand morphology and surface modeling. Prior methods typically rely on either contact maps or dense implicit descriptors to represent interaction, but these representations are often incomplete or computationally expensive and redundant. We propose InterMASH, a unified geometric representation that establishes cross-embodiment correspondence using sphere-fixed anchors. At each anchor, low-degree spherical harmonics compactly encode local hand geometry, object geometry, and contact, forming an explicit and interpretable token sequence. Building on this natively tokenized structure, we introduce a conditional Diffusion Transformer that operates directly in the proposed InterMASH representation space and jointly generates hand geometry and contact, improving consistency and physical plausibility. Our method achieves competitive performance with state-of-the-art methods on key physical feasibility metrics in a large-scale ShadowHand benchmark, supports joint training across multiple hands, and shows that cross-embodiment fine-tuning with human grasp data can improve robotic grasp success and diversity. Project page is available at https://inter-mash.github.io/.
发表机构
- University of Science and Technology of China（中国科学技术大学）
- Jiangsu Key Laboratory of AI for Industries and Institute of AI for Industries Chinese Academy of Sciences（江苏省人工智能产业重点实验室及中国科学院人工智能产业研究院）
- Shenzhen University（深圳大学）
机构由 AI 辅助整理，请以论文原文为准。
