MIME: Human-Aware 3D Scene Generation

TL;DR

MIME is a generative model that creates realistic 3D indoor scenes based on human movement data, improving diversity and plausibility of generated environments by leveraging human motion cues.

Contribution

This work introduces MIME, a novel transformer-based model that generates furniture layouts from human movement data, a reverse approach to existing scene generation methods.

Findings

MIME produces more diverse scenes than previous methods.

Scenes generated by MIME are more plausible and consistent with human movement.

The dataset was extended with 3D human annotations for training.

Abstract

Generating realistic 3D worlds occupied by moving humans has many applications in games, architecture, and synthetic data creation. But generating such scenes is expensive and labor intensive. Recent work generates human poses and motions given a 3D scene. Here, we take the opposite approach and generate 3D indoor scenes given 3D human motion. Such motions can come from archival motion capture or from IMU sensors worn on the body, effectively turning human movement in a "scanner" of the 3D world. Intuitively, human movement indicates the free-space in a room and human contact indicates surfaces or objects that support activities such as sitting, lying or touching. We propose MIME (Mining Interaction and Movement to infer 3D Environments), which is a generative model of indoor scenes that produces furniture layouts that are consistent with the human movement. MIME uses an auto-regressive transformer architecture that takes the already generated objects in the scene as well as the human motion as input, and outputs the next plausible object. To train MIME, we build a dataset by populating the 3D FRONT scene dataset with 3D humans. Our experiments show that MIME produces more diverse and plausible 3D scenes than a recent generative scene method that does not know about human movement. Code and data will be available for research at https://mime.is.tue.mpg.de.