PINO: Person-Interaction Noise Optimization for Long-Duration and Customizable Motion Generation of Arbitrary-Sized Groups

TL;DR

PINO is a training-free framework that generates realistic, customizable multi-person interactions by decomposing complex group dynamics into pairwise interactions and optimizing noise with physics-based penalties.

Contribution

It introduces a novel, training-free method that leverages pretrained two-person interaction models and physics-based constraints for flexible group motion generation.

Findings

Generates realistic multi-person interactions with physical coherence.

Allows user control over orientation, speed, and spatial relations.

Works for groups of arbitrary size without additional training.

Abstract

Generating realistic group interactions involving multiple characters remains challenging due to increasing complexity as group size expands. While existing conditional diffusion models incrementally generate motions by conditioning on previously generated characters, they rely on single shared prompts, limiting nuanced control and leading to overly simplified interactions. In this paper, we introduce Person-Interaction Noise Optimization (PINO), a novel, training-free framework designed for generating realistic and customizable interactions among groups of arbitrary size. PINO decomposes complex group interactions into semantically relevant pairwise interactions, and leverages pretrained two-person interaction diffusion models to incrementally compose group interactions. To ensure physical plausibility and avoid common artifacts such as overlapping or penetration between characters, PINO employs physics-based penalties during noise optimization. This approach allows precise user control over character orientation, speed, and spatial relationships without additional training. Comprehensive evaluations demonstrate that PINO generates visually realistic, physically coherent, and adaptable multi-person interactions suitable for diverse animation, gaming, and robotics applications.