Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos

TL;DR

Agent-to-Sim (ATS) is a framework that learns 3D interactive behavior models of animals and humans from casual, long-term monocular videos, enabling realistic simulation and real-to-sim transfer.

Contribution

ATS introduces a non-invasive method to learn persistent 3D behavior models from longitudinal videos using a novel registration and generative modeling approach.

Findings

Successfully models behaviors of pets and humans from monocular videos.

Enables realistic simulation of agent behaviors in virtual environments.

Provides a new way to learn interactive behaviors without marker-based tracking.

Abstract

We present Agent-to-Sim (ATS), a framework for learning interactive behavior models of 3D agents from casual longitudinal video collections. Different from prior works that rely on marker-based tracking and multiview cameras, ATS learns natural behaviors of animal and human agents non-invasively through video observations recorded over a long time-span (e.g., a month) in a single environment. Modeling 3D behavior of an agent requires persistent 3D tracking (e.g., knowing which point corresponds to which) over a long time period. To obtain such data, we develop a coarse-to-fine registration method that tracks the agent and the camera over time through a canonical 3D space, resulting in a complete and persistent spacetime 4D representation. We then train a generative model of agent behaviors using paired data of perception and motion of an agent queried from the 4D reconstruction. ATS enables real-to-sim transfer from video recordings of an agent to an interactive behavior simulator. We demonstrate results on pets (e.g., cat, dog, bunny) and human given monocular RGBD videos captured by a smartphone.