DEAL-Grasp: Decoupled Alignment Representation for Geometry-Aware Dexterous Grasp Generation

2026-09-23

AI Summary

为了解决现有方法在生成灵巧抓握时的不稳定性和物理不真实性问题，DEAL-Grasp通过解耦对齐表示法和异构状态流匹配来生成更稳定的抓握姿态。

Abstract

Synthesizing realistic articulated hand-object interactions is a fundamental problem in virtual reality, embodied intelligence, and digital human applications. Existing methods for dexterous grasp synthesis typically regress or denoise poses in a joint space that couples global rigid motion with local articulation, which often yields unstable samples and physically implausible contacts. We introduce DEAL-Grasp, built upon the Decoupled Alignment (DEAL) representation, which reformulates grasp synthesis as alignment-space generation: the interaction state comprises task-space geometric anchors and articulation parameters, from which the rigid transform is recovered via closed-form Procrustes alignment while preserving local articulation. On this mixed state, we model grasp generation using heterogeneous-state flow matching with component-wise vector fields, incorporating time-adaptive physical regularization during training. At inference, grasps are synthesized solely by integrating the learned vector field, without test-time optimization or auxiliary physical guidance. Across MultiDex and zero-shot RealDex benchmarks, DEAL-Grasp attains high force-perturbation success rates alongside minimal penetration and high diversity of generated grasps, while substantially reducing native inference latency compared to optimization-heavy baselines. The project page is available at https://wmtlab.github.io/DEAL-Grasp/.

Problem

• dexterous grasp
• articulated hand-object interactions
• unstable samples
• physically implausible contacts

Innovation

• Decoupled Alignment
• Procrustes alignment
• heterogeneous-state flow matching
• time-adaptive physical regularization