Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Philippe Weinzaepfel"'
Autor:
Martin Humenberger, Yohann Cabon, Noé Pion, Philippe Weinzaepfel, Donghwan Lee, Nicolas Guérin, Torsten Sattler, Gabriela Csurka
Publikováno v:
International Journal of Computer Vision. 130:1811-1836
Visual localization, i.e., camera pose estimation in a known scene, is a core component of technologies such as autonomous driving and augmented reality. State-of-the-art localization approaches often rely on image retrieval techniques for one of two
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c5f11c0756e0fc1c63968609806c0de3
https://doi.org/10.1007/s11263-022-01615-7
https://doi.org/10.1007/s11263-022-01615-7
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7a65315a4bed9e86d13b21c7479c3ab6
https://doi.org/10.1109/cvpr52688.2022.00390
https://doi.org/10.1109/cvpr52688.2022.00390
Publikováno v:
International Journal of Computer Vision
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=r3c4b2081b22::c5f11c0756e0fc1c63968609806c0de3
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200670
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d9c0c7301e834b5fe073f4b448ca923
https://doi.org/10.1007/978-3-031-20068-7_24
https://doi.org/10.1007/978-3-031-20068-7_24
Autor:
Fabien Baradel, Romain Bregier, Thibault Groueix, Philippe Weinzaepfel, Yannis Kalantidis, Gregory Rogez
Training state-of-the-art models for human pose estimation in videos requires datasets with annotations that are really hard and expensive to obtain. Although transformers have been recently utilized for body pose sequence modeling, related methods r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::35b349aed332e80cbff64a202d5605ca
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200670
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5aba2cec31bebfc42240f3982701cec3
https://doi.org/10.1007/978-3-031-20068-7_20
https://doi.org/10.1007/978-3-031-20068-7_20
Autor:
Fabien Baradel, Thibault Groueix, Philippe Weinzaepfel, Romain Bregier, Yannis Kalantidis, Gregory Rogez
Training state-of-the-art models for human body pose and shape recovery from images or videos requires datasets with corresponding annotations that are really hard and expensive to obtain. Our goal in this paper is to study whether poses from 3D Moti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2b9694258d238fdc32c5eaf7b234c8fa
http://arxiv.org/abs/2110.09243
http://arxiv.org/abs/2110.09243
Autor:
Yonghan Lee, Martin Humenberger, Suyong Yeon, Philippe Weinzaepfel, Gabriela Csurka, Nicolas Guérin, Soo-Hyun Ryu, Cheolho Han, Donghwan Lee, Deok-Hwa Kim, Yohann Cabon
Publikováno v:
CVPR
Estimating the precise location of a camera using visual localization enables interesting applications such as augmented reality or robot navigation. This is particularly useful in indoor environments where other localization technologies, such as GN
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c747458a36469092fd90e72a14132331
http://arxiv.org/abs/2105.08941
http://arxiv.org/abs/2105.08941
Autor:
Grégory Rogez, Jens Lundell, Tran Nguyen Le, Ville Kyrki, Francesco Verdoja, Enric Corona, Philippe Weinzaepfel, Francesc Moreno-Noguer
Publikováno v:
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
ICRA
Digital.CSIC. Repositorio Institucional del CSIC
instname
Universitat Politècnica de Catalunya (UPC)
ICRA
Digital.CSIC. Repositorio Institucional del CSIC
instname
Trabajo presentado en el International Conference on Robotics and Automation (ICRA), celebrado de forma híbrida (virtual y presencial), desde Xian (China), del 30 de mayo al 5 de junio de 2021
While there exists many methods for manipulating ri
While there exists many methods for manipulating ri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::16308d02aeddc0a27b65fd4eb43e44ae
http://arxiv.org/abs/2012.09696
http://arxiv.org/abs/2012.09696
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585730
ECCV (26)
ECCV (26)
We introduce DOPE, the first method to detect and estimate whole-body 3D human poses, including bodies, hands and faces, in the wild. Achieving this level of details is key for a number of applications that require understanding the interactions of t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a14e7ad6ed70ed1fcb2721e1995734b5
https://doi.org/10.1007/978-3-030-58574-7_23
https://doi.org/10.1007/978-3-030-58574-7_23