StableGrasp: Reconstructing Physically Stable Human Hand Grasps from Single Images

2026-10-06

AI Summary

This study addresses the dual challenges of insufficient physical stability and difficult control objective estimation in single-image human hand grasp reconstruction. To overcome these limitations, this work proposes a differentiable physics-based optimization framework that explicitly decouples visual geometry from control objectives. By minimizing kinetic energy, the method jointly optimizes hand pose geometry and force control parameters, incorporating regularization terms to preserve visual consistency and geometric plausibility. The proposed approach generates significantly more stable grasping poses while maintaining visual fidelity, comprehensively outperforming existing strategies. Ultimately, this work establishes a new paradigm for physically plausible reconstruction of human hand interactions.

Abstract

Reconstructing a physically stable human grasp from a single RGB image is challenging because physically modeling grasps is itself difficult, and the problem requires estimating not only a visually constrained hand pose but also a control target that stabilizes the grasp. Existing methods either model only visual hand geometry without considering physics, or rely on less plausible physical modeling, which limits the physical validity of the resulting grasps. In this paper, we present StableGrasp, a differentiable simulation-based optimization framework that explicitly separates the visual hand pose from the control target that determines the grasping forces. Our method jointly optimizes hand geometry and control by minimizing the kinetic energy of the grasp in a differentiable simulator, while regularizing the hand geometry to preserve visual consistency and geometric plausibility. The reconstructed grasps are substantially more stable under rigorous physical simulation, while remaining visually consistent with the input images and geometrically plausible. Experiments show that our approach produces far more stable grasps than alternative hand-control strategies, benefiting visual-only grasp reconstruction pipelines by turning their outputs into physically stable grasps.

Problem

• grasp reconstruction
• physical stability
• single image
• hand pose estimation
• differentiable simulation

Innovation

• Differentiable Simulation
• Physically Stable Grasp
• Hand-Object Interaction
• Pose-Control Decoupling
• Single Image Reconstruction