HOIDiNi: Human-Object Interaction through Diffusion Noise Optimization

TL;DR

HOIDiNi is a diffusion-based framework that synthesizes realistic human-object interactions from text prompts, balancing contact accuracy and motion naturalness through a novel noise optimization approach.

Contribution

It introduces Diffusion Noise Optimization (DNO) for HOI synthesis, separating object contact planning from human motion refinement for improved realism and control.

Findings

Outperforms prior methods in contact accuracy and realism

Generates complex interactions like grasping and placement from text

Achieves high-quality, controllable HOI synthesis

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 realism and physical correctness, 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 dataset alone clearly indicate HOIDiNi outperforms prior works and baselines in contact accuracy, physical validity, 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. https://hoidini.github.io.