Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Michael Strecke"'
Autor:
Michael Strecke, Joerg Stueckler
Publikováno v:
2021 International Conference on 3D Vision (3DV).
Differentiable physics is a powerful tool in computer vision and robotics for scene understanding and reasoning about interactions. Existing approaches have frequently been limited to objects with simple shape or shapes that are known in advance. In
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::299e7c36613c7a52847090dbd9d977e3
https://doi.org/10.1109/3dv53792.2021.00020
https://doi.org/10.1109/3dv53792.2021.00020
Autor:
Michael Strecke, Jörg Stückler
Publikováno v:
CVPR
Dynamic scene understanding is an essential capability in robotics and VR/AR. In this paper we propose Co-Section, an optimization-based approach to 3D dynamic scene reconstruction, which infers hidden shape information from intersection constraints.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b82cb27bb50bf3af5515f8090da4aa50
http://arxiv.org/abs/2004.04630
http://arxiv.org/abs/2004.04630
Autor:
Michael Strecke, Joerg Stueckler
Publikováno v:
ICCV
The majority of approaches for acquiring dense 3D environment maps with RGB-D cameras assumes static environments or rejects moving objects as outliers. The representation and tracking of moving objects, however, has significant potential for applica
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9369ea524975b94119d6cac821a929c9
http://arxiv.org/abs/1904.11781
http://arxiv.org/abs/1904.11781
Autor:
Bastian Goldluecke, Michael Strecke
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030129385
GCPR
GCPR
We propose a novel idea to introduce regularization based on second order total generalized variation (\(\text {TGV}\)) into optimization frameworks based on functional lifting. The proposed formulation extends a recent sublabel-accurate relaxation f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5c551adcc6a722d521cbb540cf433314
https://doi.org/10.1007/978-3-030-12939-2_19
https://doi.org/10.1007/978-3-030-12939-2_19
Autor:
Maximilian Diebold, Marcel Gutsche, Anna Alperovich, Ole Johannsen, Shuo Zhang, Jaesik Park, Marco Carli, Michele Brizzi, Hae-Gon Jeon, Yu-Wing Tai, Sven Wanner, Bastian Goldluecke, Jinsun Park, Yunsu Bok, Zhang Xiong, Hao Sheng, Jingyi Yu, Qing Wang, Lipeng Si, Katrin Honauer, In So Kweon, Antonin Sulc, Gyeongmin Choe, Michael Strecke, Hendrik Schilling, Hao Zhu, Federica Battisti, Ting-Chun Wang
Publikováno v:
CVPR Workshops
This paper presents the results of the depth estimation challenge for dense light fields, which took place at the second workshop on Light Fields for Computer Vision (LF4CV) in conjunction with CVPR 2017. The challenge consisted of submission to a re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ffa868510b01306b9d4840d36d0d24d
http://hdl.handle.net/11577/3363391
http://hdl.handle.net/11577/3363391
Publikováno v:
CVPR
We present a fully convolutional autoencoder for light fields, which jointly encodes stacks of horizontal and vertical epipolar plane images through a deep network of residual layers. The complex structure of the light field is thus reduced to a comp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bae845f9ab28a17998b4aa8ce4e723db
https://doi.org/10.1109/cvpr.2018.00953
https://doi.org/10.1109/cvpr.2018.00953
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319781983
EMMCVPR
EMMCVPR
In this work, we focus on the problem of intrinsic scene decomposition in light fields. Our main contribution is a novel prior to cope with cast shadows and inter-reflections. In contrast to other approaches which model inter-reflection based only on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::630ace53b8d332b1956b5464a6d2f14e
https://doi.org/10.1007/978-3-319-78199-0_26
https://doi.org/10.1007/978-3-319-78199-0_26
Publikováno v:
CVPR
We introduce a novel approach to jointly estimate consistent depth and normal maps from 4D light fields, with two main contributions. First, we build a cost volume from focal stack symmetry. However, in contrast to previous approaches, we introduce p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bbef2c69b2c2547043d2acda763ec2d8
https://doi.org/10.1109/cvpr.2017.271
https://doi.org/10.1109/cvpr.2017.271
Autor:
Michael Strecke
Publikováno v:
intensiv. 18:314-315
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d3682df4564c017ae075c7fa7610022f
https://doi.org/10.1055/s-0030-1268018
https://doi.org/10.1055/s-0030-1268018