EFF-Grasp: Energy-Field Flow Matching for Physics-Aware Dexterous Grasp Generation

TL;DR

EFF-Grasp introduces a deterministic flow-matching framework for physics-aware dexterous grasp generation, improving efficiency and physical feasibility over traditional diffusion-based methods by using energy-guided trajectories.

Contribution

The paper presents a novel flow-matching approach reformulating grasp synthesis as a deterministic ODE, with a physics-aware energy guidance strategy that does not require additional training.

Findings

Achieves superior grasp quality and physical feasibility

Requires fewer sampling steps than diffusion-based methods

Demonstrates effectiveness on five benchmark datasets

Abstract

Denoising generative models have recently become the dominant paradigm for dexterous grasp generation, owing to their ability to model complex grasp distributions from large-scale data. However, existing diffusion-based methods typically formulate generation as a stochastic differential equation (SDE), which often requires many sequential denoising steps and introduces trajectory instability that can lead to physically infeasible grasps. In this paper, we propose EFF-Grasp, a novel Flow-Matching-based framework for physics-aware dexterous grasp generation. Specifically, we reformulate grasp synthesis as a deterministic ordinary differential equation (ODE) process, which enables efficient and stable generation through smooth probability flows. To further enforce physical feasibility, we introduce a training-free physics-aware energy guidance strategy. Our method defines an energy-guided target distribution using adapted explicit physical energy functions that capture key grasp constraints, and estimates the corresponding guidance term via a local Monte Carlo approximation during inference. In this way, EFF-Grasp dynamically steers the generation trajectory toward physically feasible regions without requiring additional physics-based training or simulation feedback. Extensive experiments on five benchmark datasets show that EFF-Grasp achieves superior performance in grasp quality and physical feasibility, while requiring substantially fewer sampling steps than diffusion-based baselines.