LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals

Gosztolai A, Günel S, Lobato-Ríos V, Pietro Abrate M, Morales D, Rhodin H, Fua P, Ramdya P (2021)
Nature Methods 18(8): 975-981.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Gosztolai, Adam; Günel, Semih; Lobato-Ríos, Victor; Pietro Abrate, Marco; Morales, Daniel; Rhodin, HelgeUniBi ; Fua, Pascal; Ramdya, Pavan
Abstract / Bemerkung
Markerless three-dimensional (3D) pose estimation has become an indispensable tool for kinematic studies of laboratory animals. Most current methods recover 3D poses by multi-view triangulation of deep network-based two-dimensional (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 macaques, and in circumstances where 3D triangulation is impractical or impossible. Our framework achieves accurate lifting for stereotypical and nonstereotypical behaviors from different camera angles. Thus, LiftPose3D permits high-quality 3D pose estimation in the absence of complex camera arrays and tedious calibration procedures and despite occluded body parts in freely behaving animals.
Erscheinungsjahr
2021
Zeitschriftentitel
Nature Methods
Band
18
Ausgabe
8
Seite(n)
975-981
ISSN
1548-7091
eISSN
1548-7105
Page URI
https://pub.uni-bielefeld.de/record/2991921

Zitieren

Gosztolai A, Günel S, Lobato-Ríos V, et al. LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals. Nature Methods. 2021;18(8):975-981.
Gosztolai, A., Günel, S., Lobato-Ríos, V., Pietro Abrate, M., Morales, D., Rhodin, H., Fua, P., et al. (2021). LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals. Nature Methods, 18(8), 975-981. https://doi.org/10.1038/s41592-021-01226-z
Gosztolai, Adam, Günel, Semih, Lobato-Ríos, Victor, Pietro Abrate, Marco, Morales, Daniel, Rhodin, Helge, Fua, Pascal, and Ramdya, Pavan. 2021. “LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals”. Nature Methods 18 (8): 975-981.
Gosztolai, A., Günel, S., Lobato-Ríos, V., Pietro Abrate, M., Morales, D., Rhodin, H., Fua, P., and Ramdya, P. (2021). LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals. Nature Methods 18, 975-981.
Gosztolai, A., et al., 2021. LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals. Nature Methods, 18(8), p 975-981.
A. Gosztolai, et al., “LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals”, Nature Methods, vol. 18, 2021, pp. 975-981.
Gosztolai, A., Günel, S., Lobato-Ríos, V., Pietro Abrate, M., Morales, D., Rhodin, H., Fua, P., Ramdya, P.: LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals. Nature Methods. 18, 975-981 (2021).
Gosztolai, Adam, Günel, Semih, Lobato-Ríos, Victor, Pietro Abrate, Marco, Morales, Daniel, Rhodin, Helge, Fua, Pascal, and Ramdya, Pavan. “LiftPose3D, a deep learning-based approach for transforming two-dimensional to three-dimensional poses in laboratory animals”. Nature Methods 18.8 (2021): 975-981.

Link(s) zu Volltext(en)
Access Level
OA Open Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Quellen

Preprint: 10.1101/2020.09.18.292680v2

Suchen in

Google Scholar