Optical Mouse: 3D Mouse Pose From Single-View Video

TL;DR

This paper introduces a novel method to accurately estimate 3D mouse poses from single-view videos, enabling non-invasive health monitoring and improved behavioral analysis.

Contribution

The proposed approach is the first to infer detailed 3D mouse poses from monocular videos, enhancing health assessment capabilities in animal models.

Findings

Accurately estimates 3D mouse pose from monocular video

Improves classification of health-related attributes over 2D data

Estimates stride length despite occlusions

Abstract

We present a method to infer the 3D pose of mice, including the limbs and feet, from monocular videos. Many human clinical conditions and their corresponding animal models result in abnormal motion, and accurately measuring 3D motion at scale offers insights into health. The 3D poses improve classification of health-related attributes over 2D representations. The inferred poses are accurate enough to estimate stride length even when the feet are mostly occluded. This method could be applied as part of a continuous monitoring system to non-invasively measure animal health.