Gaze-guided Hand-Object Interaction Synthesis: Dataset and Method

TL;DR

This paper introduces GazeHOI, a new dataset and a diffusion-based model for synthesizing hand-object interactions guided by gaze data, addressing challenges of data sparsity and motion plausibility in AR/VR applications.

Contribution

The paper presents the first dataset capturing 3D gaze, hand, and object interactions and proposes a novel diffusion model with manifold guidance for realistic, gaze-guided motion synthesis.

Findings

The GHO-Diffusion model effectively generates plausible hand-object motions.

GazeHOI dataset enables detailed analysis of gaze-guided interactions.

The method achieves high consistency with gaze contact and interaction trajectories.

Abstract

Gaze plays a crucial role in revealing human attention and intention, particularly in hand-object interaction scenarios, where it guides and synchronizes complex tasks that require precise coordination between the brain, hand, and object. Motivated by this, we introduce a novel task: Gaze-Guided Hand-Object Interaction Synthesis, with potential applications in augmented reality, virtual reality, and assistive technologies. To support this task, we present GazeHOI, the first dataset to capture simultaneous 3D modeling of gaze, hand, and object interactions. This task poses significant challenges due to the inherent sparsity and noise in gaze data, as well as the need for high consistency and physical plausibility in generating hand and object motions. To tackle these issues, we propose a stacked gaze-guided hand-object interaction diffusion model, named GHO-Diffusion. The stacked design effectively reduces the complexity of motion generation. We also introduce HOI-Manifold Guidance during the sampling stage of GHO-Diffusion, enabling fine-grained control over generated motions while maintaining the data manifold. Additionally, we propose a spatial-temporal gaze feature encoding for the diffusion condition and select diffusion results based on consistency scores between gaze-contact maps and gaze-interaction trajectories. Extensive experiments highlight the effectiveness of our method and the unique contributions of our dataset. More details in https://takiee.github.io/gaze-hoi/.