Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schr\"odinger Bridges

TL;DR

This paper introduces a novel vision-based method for translating grasp configurations between different robotic hands using Schr"odinger Bridges, enabling stable and physically consistent grasp transfer without paired data.

Contribution

It presents a new probabilistic framework for grasp translation that leverages Schr"odinger Bridges and physics-informed costs, advancing heterogeneous robotic manipulation.

Findings

Successfully transfers grasps across diverse hand morphologies.

Generates stable, physically grounded grasps with strong generalization.

Bridges vision-based grasping with probabilistic generative modeling.

Abstract

We propose a new approach to vision-based dexterous grasp translation, which aims to transfer grasp intent across robotic hands with differing morphologies. Given a visual observation of a source hand grasping an object, our goal is to synthesize a functionally equivalent grasp for a target hand without requiring paired demonstrations or hand-specific simulations. We frame this problem as a stochastic transport between grasp distributions using the Schr\"odinger Bridge formalism. Our method learns to map between source and target latent grasp spaces via score and flow matching, conditioned on visual observations. To guide this translation, we introduce physics-informed cost functions that encode alignment in base pose, contact maps, wrench space, and manipulability. Experiments across diverse hand-object pairs demonstrate our approach generates stable, physically grounded grasps with strong generalization. This work enables semantic grasp transfer for heterogeneous manipulators and bridges vision-based grasping with probabilistic generative modeling. Additional details at https://grasp2grasp.github.io/