VolCo: Volumetric Contact for High-Fidelity Human Grasp Generation

2026-10-07

AI Summary

This study addresses the limitations of existing surface contact representations, which often result in hand-object penetration and loss of fine-grained details. To overcome these challenges, this work proposes a novel volumetric grid contact representation. The method establishes a hierarchical architecture that integrates local geometric details with global structure, leveraging a 3D variational autoencoder, a prior-guided diffusion model, and signed distance fields to synthesize high-fidelity human grasping poses. Experimental evaluations demonstrate that the proposed approach achieves state-of-the-art performance on standard benchmark datasets, significantly reducing penetration rates while enhancing overall grasp stability.

Abstract

Accurate contact modeling is fundamental to understanding hand-object interaction, yet existing contact representations are typically restricted to object surfaces and rely on hand-crafted rules to recover contact details, leading to severe penetrations and implausible results. To better exploit the rich detail in motion-capture data, we introduce Volumetric Contact (VolCo), a representation that expands surface points to a set of 3D volumetric grids. VolCo encodes 3D contact that allows precise hand part recovery, and is organized in an inherent hierarchy: local contact details within each volume and global hand geometry across all volumes. Our framework, VolCoDiff, employs two modules to capture local and global features following this hierarchy. For local contact details, we use a 3D variational autoencoder to model the possible hand configurations conditioned on the local object signed distance field (SDF). For global hand geometry, we design a prior-guided diffusion model that learns the distribution of compressed latent features aggregated from the volumetric grids. We evaluate our method on two benchmark datasets and demonstrate state-of-the-art performance in penetration and stability, indicating the capability to generate tight grasps with much less severe penetrations. Our code is available at https://github.com/chzh9311/volco.

Problem

• Human Grasp Generation
• Contact Modeling
• Hand-Object Interaction
• Volumetric Contact

Innovation

• Volumetric Contact
• Hand-Object Interaction
• 3D Variational Autoencoder
• Signed Distance Field
• Diffusion Model