Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/167042
COMPARTIR / EXPORTAR:
SHARE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Título: | 3D human pose estimation from a single image via distance matrix regression |
Autor: | Moreno-Noguer, Francesc CSIC ORCID | Fecha de publicación: | 2017 | Editor: | Institute of Electrical and Electronics Engineers | Citación: | IEEE Conference on Computer Vision and Pattern Recognition: 1561-1570 (2017) | Resumen: | This paper addresses the problem of 3D human pose estimation from a single image. We follow a standard two-step pipeline by first detecting the 2D position of the N body joints, and then using these observations to infer 3D pose. For the first step, we use a recent CNN-based detector. For the second step, most existing approaches perform 2N-to-3N regression of the Cartesian joint coordinates. We show that more precise pose estimates can be obtained by representing both the 2D and 3D human poses using $Ntimes N$ distance matrices, and formulating the problem as a 2D-to-3D distance matrix regression. For learning such a regressor we leverage on simple Neural Network architectures, which by construction, enforce positivity and symmetry of the predicted matrices. The approach has also the advantage to naturally handle missing observations and allowing to hypothesize the position of non-observed joints. Quantitative results on Humaneva and Human3.6M datasets demonstrate consistent performance gains over state-of-the-art. Qualitative evaluation on the images in-the-wild of the LSP dataset, using the regressor learned on Human3.6M, reveals very promising generalization results. | Descripción: | Trabajo presentado a la 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), celebrada en Honolulu, Hawaii (US) del 21 al 26 de julio de 2016. | Versión del editor: | https://doi.org/10.1109/CVPR.2017.170 | URI: | http://hdl.handle.net/10261/167042 | DOI: | 10.1109/CVPR.2017.170 | Identificadores: | doi: 10.1109/CVPR.2017.170 isbn: 978-1-5386-0458-8 |
Aparece en las colecciones: | (IRII) Libros y partes de libros |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
3Dregresion.pdf | 6,52 MB | Unknown | Visualizar/Abrir |
CORE Recommender
Page view(s)
423
checked on 19-abr-2024
Download(s)
334
checked on 19-abr-2024
Google ScholarTM
Check
Altmetric
Altmetric
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.