HOIDiNi: Human-Object Interaction through Diffusion Noise Optimization

Roey Ron, Guy Tevet, Haim Sawdayee, Amit H. Bermano

Keywords: motion synthesis, interaction synthesis, diffusion model

Abstract: We present HOIDiNi, a text-driven diffusion framework for synthesizing realistic and plausible human-object interaction (HOI). HOI generation is extremely challenging since it induces strict contact accuracies alongside a diverse motion manifold. While current literature trades off between realistic motions and accurate contacts, HOIDiNi optimizes directly in the noise space of a pretrained diffusion model using Diffusion Noise Optimization (DNO), achieving both. This is made feasible thanks to our observation that the problem can be separated into two phases: an object-centric phase, primarily making discrete choices of hand-object contact locations, and a human-centric phase that refines the full-body motion to realize this blueprint. This structured approach allows for precise hand-object contact without compromising motion naturalness. Quantitative, qualitative, and subjective evaluations on the GRAB and OMOMO datasets clearly indicate HOIDiNi outperforms prior works and baselines in contact accuracy, visual plausibility, and overall quality. Our results demonstrate the ability to generate complex, controllable interactions, including grasping, placing, and full-body coordination, driven solely by textual prompts.

Primary Area: generative models

Submission Number: 9718