Physics-based Scene Layout Generation from Human Motion

TL;DR

This paper introduces a physics-based method for automatic scene layout generation that ensures realistic human-scene interactions by optimizing scene placement and character motion simultaneously using reinforcement learning.

Contribution

It presents a novel physics-based approach that jointly optimizes scene layout and human motion, overcoming artifacts and improving generalization over previous methods.

Findings

Achieves physically plausible scene layouts with realistic human interaction.

Outperforms previous kinematics-based methods in scene reconstruction.

Demonstrates effectiveness on motions from SAMP and PROX datasets.

Abstract

Creating scenes for captured motions that achieve realistic human-scene interaction is crucial for 3D animation in movies or video games. As character motion is often captured in a blue-screened studio without real furniture or objects in place, there may be a discrepancy between the planned motion and the captured one. This gives rise to the need for automatic scene layout generation to relieve the burdens of selecting and positioning furniture and objects. Previous approaches cannot avoid artifacts like penetration and floating due to the lack of physical constraints. Furthermore, some heavily rely on specific data to learn the contact affordances, restricting the generalization ability to different motions. In this work, we present a physics-based approach that simultaneously optimizes a scene layout generator and simulates a moving human in a physics simulator. To attain plausible and realistic interaction motions, our method explicitly introduces physical constraints. To automatically recover and generate the scene layout, we minimize the motion tracking errors to identify the objects that can afford interaction. We use reinforcement learning to perform a dual-optimization of both the character motion imitation controller and the scene layout generator. To facilitate the optimization, we reshape the tracking rewards and devise pose prior guidance obtained from our estimated pseudo-contact labels. We evaluate our method using motions from SAMP and PROX, and demonstrate physically plausible scene layout reconstruction compared with the previous kinematics-based method.