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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Gengshan, Bajcsy, Andrea, Saito, Shunsuke, Kanazawa, Angjoo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929552239886336
author Yang, Gengshan
Bajcsy, Andrea
Saito, Shunsuke
Kanazawa, Angjoo
author_facet Yang, Gengshan
Bajcsy, Andrea
Saito, Shunsuke
Kanazawa, Angjoo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16259
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos
Yang, Gengshan
Bajcsy, Andrea
Saito, Shunsuke
Kanazawa, Angjoo
Computer Vision and Pattern Recognition
Graphics
Robotics
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.
title Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos
topic Computer Vision and Pattern Recognition
Graphics
Robotics
url https://arxiv.org/abs/2410.16259