Open Collections

Abstract

Neural-network‑based pose estimation models have become increasingly popular for quantitative analysis of mouse behavior, yet most recordings still use a single 2‑D camera view and therefore lack the depth cues needed for accurate 3‑D kinematics. Existing open‑source 3‑D mouse datasets for training deep-learning models cover only a narrow range of environments and do not generalize well to various laboratory settings. To overcome these limitations, I introduce PyMouse Lifter, a pipeline that automatically reconstructs 3‑D mouse poses from ordinary 2-D top‑view videos with minimal manual 2-D annotation. PyMouse Lifter combines (i) an anatomically realistic 3‑D mouse model for automated data synthesis, (ii) a monocular depth estimation model, and (iii) a 2‑D key‑point estimation model, enabling accurate 3‑D lifting (model-based 3D inference) in virtually any open‑field arena without using depth or multiple camera views for reconstruction. I validate the system on multiple datasets against depth‑camera ground truth and show that the lifted 3D trajectories yield improved behavior classification than 2‑D data and can be implemented in real time.