Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Tomas Hodan"'
Autor:
Enric Corona, Tomas Hodan, Minh Vo, Francesc Moreno-Noguer, Chris Sweeney, Richard Newcombe, Lingni Ma
This paper proposes a do-it-all neural model of human hands, named LISA. The model can capture accurate hand shape and appearance, generalize to arbitrary hand subjects, provide dense surface correspondences, be reconstructed from images in the wild
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b5bf20ab6585b4733a08fd49f0b79ccb
http://arxiv.org/abs/2204.01695
http://arxiv.org/abs/2204.01695
Autor:
Lin Huang, Tomas Hodan, Lingni Ma, Linguang Zhang, Luan Tran, Christopher Twigg, Po-Chen Wu, Junsong Yuan, Cem Keskin, Robert Wang
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200793
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a31e3442d4a33b93ccab661e1ab8b364
https://doi.org/10.1007/978-3-031-20080-9_34
https://doi.org/10.1007/978-3-031-20080-9_34
Publikováno v:
CVPR
We present a new method for estimating the 6D pose of rigid objects with available 3D models from a single RGB input image. The method is applicable to a broad range of objects, including challenging ones with global or partial symmetries. An object
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a158d3c5ce20d316dbc50ba8ff91f7f5
http://arxiv.org/abs/2004.00605
http://arxiv.org/abs/2004.00605
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585761
ECCV (30)
ECCV (30)
This paper proposes a technique for training a neural network by minimizing a surrogate loss that approximates the target evaluation metric, which may be non-differentiable. The surrogate is learned via a deep embedding where the Euclidean distance b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7b5a3530316b41094a62a078f9f23c60
https://doi.org/10.1007/978-3-030-58577-8_13
https://doi.org/10.1007/978-3-030-58577-8_13
Autor:
Treb Connell, Tomas Hodan, Jon Hanzelka, Shalev Emanuel, Brian Guenter, Vibhav Vineet, Ran Gal, Pedro Urbina, Sudipta N. Sinha
Publikováno v:
ICIP
We present an approach to synthesize highly photorealistic images of 3D object models, which we use to train a convolutional neural network for detecting the objects in real images. The proposed approach has three key ingredients: (1) 3D object model
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::91abe85b32bf2a0d797a8a34fea07d00
https://doi.org/10.1109/icip.2019.8803821
https://doi.org/10.1109/icip.2019.8803821
Autor:
Tae-Kyun Kim, Tomas Hodan, Ales Leonardis, Bertram Drost, Rigas Kouskouridas, Carsten Rother, Vincent Lepetit, Carsten Steger, Federico Tombari, Frank Michel, Krzysztof Walas, Caner Sahin, Jiri Matas, Thibault Groueix, Kostas E. Bekris
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030110086
ECCV Workshops (1)
ECCV Workshops (1)
This document summarizes the 4th International Workshop on Recovering 6D Object Pose which was organized in conjunction with ECCV 2018 in Munich. The workshop featured four invited talks, oral and poster presentations of accepted workshop papers, and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::941a0076f5e94baba6d1cbaca31098a6
https://doi.org/10.1007/978-3-030-11009-3_36
https://doi.org/10.1007/978-3-030-11009-3_36
Autor:
Dirk Kraft, Tae-Kyun Kim, Caner Sahin, Carsten Rother, Stephan Ihrke, Eric Brachmann, Xenophon Zabulis, Tomas Hodan, Wadim Kehl, Frank Michel, Jiri Matas, Bertram Drost, Joel Vidal, Federico Tombari, Anders Buch, Fabian Manhardt
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012489
ECCV (10)
ECCV (10)
We propose a benchmark for 6D pose estimation of a rigid object from a single RGB-D input image. The training data consists of a texture-mapped 3D object model or images of the object in known 6D poses. The benchmark comprises of: (i) eight datasets
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::465eb7f138dc2ffa7c56773c335ddfc9
https://doi.org/10.1007/978-3-030-01249-6_2
https://doi.org/10.1007/978-3-030-01249-6_2
Autor:
Jiri Matas, Tomas Hodan, Xenophon Zabulis, Manolis I. A. Lourakis, Stepan Obdrzalek, Pavel Haluza
Publikováno v:
WACV
We introduce T-LESS, a new public dataset for estimating the 6D pose, i.e. translation and rotation, of texture-less rigid objects. The dataset features thirty industry-relevant objects with no significant texture and no discriminative color or refle
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1cfa201a4c50f2252378e2860136359
https://doi.org/10.1109/wacv.2017.103
https://doi.org/10.1109/wacv.2017.103
Publikováno v:
IROS
Despite their ubiquitous presence, texture-less objects present significant challenges to contemporary visual object detection and localization algorithms. This paper proposes a practical method for the detection and accurate 3D localization of multi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::91f3564f71f46d23e1803b72981a49fe
https://doi.org/10.1109/iros.2015.7354005
https://doi.org/10.1109/iros.2015.7354005