The Wanderings of Odysseus in 3D Scenes

TL;DR

This paper introduces GAMMA, a generative model for creating realistic, controllable, and long-term motions of diverse 3D human bodies in digital environments, enabling perpetual movement and scene contact.

Contribution

We propose a novel approach using body surface markers and variational autoencoders to generate and control long-term human motions in 3D scenes, improving realism and controllability.

Findings

GAMMA outperforms state-of-the-art methods in realism and control.

Generated motions can sustain long-distance movement over extended periods.

The method enables realistic, perpetual human motion in digital environments.

Abstract

Our goal is to populate digital environments, in which digital humans have diverse body shapes, move perpetually, and have plausible body-scene contact. The core challenge is to generate realistic, controllable, and infinitely long motions for diverse 3D bodies. To this end, we propose generative motion primitives via body surface markers, or GAMMA in short. In our solution, we decompose the long-term motion into a time sequence of motion primitives. We exploit body surface markers and conditional variational autoencoder to model each motion primitive, and generate long-term motion by implementing the generative model recursively. To control the motion to reach a goal, we apply a policy network to explore the generative model's latent space and use a tree-based search to preserve the motion quality during testing. Experiments show that our method can produce more realistic and controllable motion than state-of-the-art data-driven methods. With conventional path-finding algorithms, the generated human bodies can realistically move long distances for a long period of time in the scene. Code is released for research purposes at: \url{https://yz-cnsdqz.github.io/eigenmotion/GAMMA/}