LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals.
LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals.
复制标题
DOI:
10.1038/s41592-021-01226-z
复制
发表时间:
2021-08
期刊:
影响因子:
48
通讯作者:
Ramdya P
中科院分区:
文献类型:
--
作者:
Gosztolai A;Günel S;Lobato-Ríos V;Pietro Abrate M;Morales D;Rhodin H;Fua P;Ramdya P
Markerless 3D pose estimation has become an indispensable tool for kinematic studies of laboratory animals. Most current methods recover 3D pose by multi-view triangulation of deep network-based 2D pose estimates. However, triangulation requires multiple, synchronized cameras and elaborate calibration protocols that hinder its widespread adoption in laboratory studies. Here we describe LiftPose3D, a deep network-based method that overcomes these barriers by reconstructing 3D poses from a single 2D camera view. We illustrate LiftPose3D’s versatility by applying it to multiple experimental systems using flies, mice, rats, and macaque monkeys and in circumstances where 3D triangulation is impractical or impossible. Our framework achieves accurate lifting for stereotyped and non-stereotyped behaviors from different camera angles. Thus, LiftPose3D permits high-quality 3D pose estimation in the absence of complex camera arrays, tedious calibration procedures, and despite occluded body parts in freely behaving animals.
登录
查看更多内容
影响因子:
2.8
作者:
Isakov, Alexander;Buchanan, Sean M.;de Bivort, Benjamin
通讯作者:
de Bivort, Benjamin
影响因子:
64.8
作者:
通讯作者:
--
影响因子:
6.2
作者:
Loper, Matthew;Mahmood, Naureen;Black, Michael J.
通讯作者:
Black, Michael J.
影响因子:
25
作者:
Louis, Matthieu;Huber, Thomas;Vosshall, Leslie B.
通讯作者:
Vosshall, Leslie B.
影响因子:
16.6
作者:
Feng K;Sen R;Minegishi R;Dübbert M;Bockemühl T;Büschges A;Dickson BJ
通讯作者:
Dickson BJ