DCGrasp: Distance-aware Controllable Grasp Generation

2026-06-29

AI Summary

Existing methods for generating 3D hand–object interactions struggle to simultaneously achieve user controllability and generalization across diverse object geometries. To address this, this work proposes a controllable generation framework based on a distance-aware grasping energy term. The approach first employs a diffusion transformer to generate a distance field and an initial hand pose, followed by a pose refinement step within near-contact regions to enforce physical plausibility. The key innovation lies in the introduction of the distance field and its perception-weighted mechanism, which effectively captures semantically similar interaction patterns while remaining invariant to specific hand and object identities. This method enables high-quality, physically plausible, and user-controllable grasp synthesis, demonstrating strong generalization across a wide range of objects and hand shapes.

Abstract

Generating 3D hand-object interactions is essential for applications in robotics, XR, and synthetic data generation, where flexible controllability and strong generalization to diverse object geometries are required. However, existing methods rarely satisfy these requirements, limiting their practical applicability. We present DCGrasp, a distance-aware controllable grasp generation system built on a novel grasp energy term. This term computes Distance Profile, a signed distance from each hand vertex to the nearest object point, coupled with distance-aware weighting, effectively capturing the semantically similar hand-object interaction in near-contact regions while remaining invariant to object and hand identity. Given various controllable signals, DCGrasp first generates a Distance Profile based on a Diffusion Transformer, together with a corresponding candidate hand pose. We then refine the candidate pose through optimization, enforcing consistency between the optimized hand pose and the generated Distance Profile in near-contact regions. Our experiments show that DCGrasp produces high-quality, physically plausible grasps with flexible user control, generalizing to diverse object and hand shapes and scales. Our work establishes a robust and versatile pipeline for the synthesis of controllable 3D hand-object interactions.

Problem

• 3D hand-object interaction
• controllable grasp generation
• object geometry generalization
• grasp synthesis

Innovation

• Distance Profile
• Controllable Grasp Generation
• Diffusion Transformer
• Hand-Object Interaction
• Distance-aware Weighting