SMGDiff: Soccer Motion Generation using diffusion probabilistic models

TL;DR

SMGDiff is a two-stage diffusion-based framework that generates realistic, diverse, and controllable soccer motions in real-time, effectively modeling complex interactions between players and the ball.

Contribution

The paper introduces SMGDiff, a novel diffusion-based model with a contact guidance module and a large-scale soccer motion dataset, advancing realistic motion generation.

Findings

Outperforms existing methods in motion quality

Provides high diversity and control in generated motions

Includes a large dataset of soccer motions

Abstract

Soccer is a globally renowned sport with significant applications in video games and VR/AR. However, generating realistic soccer motions remains challenging due to the intricate interactions between the human player and the ball. In this paper, we introduce SMGDiff, a novel two-stage framework for generating real-time and user-controllable soccer motions. Our key idea is to integrate real-time character control with a powerful diffusion-based generative model, ensuring high-quality and diverse output motion. In the first stage, we instantly transform coarse user controls into diverse global trajectories of the character. In the second stage, we employ a transformer-based autoregressive diffusion model to generate soccer motions based on trajectory conditioning. We further incorporate a contact guidance module during inference to optimize the contact details for realistic ball-foot interactions. Moreover, we contribute a large-scale soccer motion dataset consisting of over 1.08 million frames of diverse soccer motions. Extensive experiments demonstrate that our SMGDiff significantly outperforms existing methods in terms of motion quality and condition alignment.