SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios

TL;DR

SViMo introduces a synchronized diffusion framework that jointly generates high-fidelity hand-object interaction videos and 3D motions, overcoming limitations of prior methods by eliminating predefined models and enhancing physical plausibility.

Contribution

The paper presents a novel synchronized diffusion approach combining visual priors and dynamic constraints for joint video and motion generation in HOI scenarios, with a closed-loop feedback mechanism.

Findings

Outperforms state-of-the-art in video and motion quality

Demonstrates strong generalization to unseen scenarios

Produces physically plausible and consistent HOI sequences

Abstract

Hand-Object Interaction (HOI) generation has significant application potential. However, current 3D HOI motion generation approaches heavily rely on predefined 3D object models and lab-captured motion data, limiting generalization capabilities. Meanwhile, HOI video generation methods prioritize pixel-level visual fidelity, often sacrificing physical plausibility. Recognizing that visual appearance and motion patterns share fundamental physical laws in the real world, we propose a novel framework that combines visual priors and dynamic constraints within a synchronized diffusion process to generate the HOI video and motion simultaneously. To integrate the heterogeneous semantics, appearance, and motion features, our method implements tri-modal adaptive modulation for feature aligning, coupled with 3D full-attention for modeling inter- and intra-modal dependencies. Furthermore, we introduce a vision-aware 3D interaction diffusion model that generates explicit 3D interaction sequences directly from the synchronized diffusion outputs, then feeds them back to establish a closed-loop feedback cycle. This architecture eliminates dependencies on predefined object models or explicit pose guidance while significantly enhancing video-motion consistency. Experimental results demonstrate our method's superiority over state-of-the-art approaches in generating high-fidelity, dynamically plausible HOI sequences, with notable generalization capabilities in unseen real-world scenarios. Project page at https://github.com/Droliven/SViMo_project.