InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion
It addresses a novel task in computer vision and graphics for applications like animation and robotics, though it builds on existing diffusion and physics-based methods.
This paper tackled the problem of anticipating 3D human-object interactions (HOIs) with dynamic objects, proposing InterDiff, a framework that uses diffusion models and physics-informed correction to generate realistic and long-term predictions, as demonstrated on multiple datasets.
This paper addresses a novel task of anticipating 3D human-object interactions (HOIs). Most existing research on HOI synthesis lacks comprehensive whole-body interactions with dynamic objects, e.g., often limited to manipulating small or static objects. Our task is significantly more challenging, as it requires modeling dynamic objects with various shapes, capturing whole-body motion, and ensuring physically valid interactions. To this end, we propose InterDiff, a framework comprising two key steps: (i) interaction diffusion, where we leverage a diffusion model to encode the distribution of future human-object interactions; (ii) interaction correction, where we introduce a physics-informed predictor to correct denoised HOIs in a diffusion step. Our key insight is to inject prior knowledge that the interactions under reference with respect to contact points follow a simple pattern and are easily predictable. Experiments on multiple human-object interaction datasets demonstrate the effectiveness of our method for this task, capable of producing realistic, vivid, and remarkably long-term 3D HOI predictions.