Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Oleksandr Sotnychenko"'
Autor:
Christian Theobalt, Miguel A. Otaduy, Mickeal Verschoor, Micah Davis, Franziska Mueller, Florian Bernard, Dan Casas, Oleksandr Sotnychenko
Publikováno v:
BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
instname
ACM Transactions on Graphics
Proceedings of ACM SIGGRAPH 2019
instname
ACM Transactions on Graphics
Proceedings of ACM SIGGRAPH 2019
We present a novel method for real-time pose and shape reconstruction of two strongly interacting hands. Our approach is the first two-hand tracking solution that combines an extensive list of favorable properties, namely it is marker-less, uses a si
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c3011099bedf78d9484c3a45f4405f97
http://arxiv.org/abs/2106.08059
http://arxiv.org/abs/2106.08059
Autor:
Dan Casas, Franziska Mueller, Christian Theobalt, Suzanne Sorli, Miguel A. Otaduy, Oleksandr Sotnychenko, Neng Qian, Florian Bernard, Jiayi Wang
Publikováno v:
BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
instname
ACM Transactions on Graphics
Proceedings of ACM SIGGRAPH Asia 2020
instname
ACM Transactions on Graphics
Proceedings of ACM SIGGRAPH Asia 2020
Tracking and reconstructing the 3D pose and geometry of two hands in interaction is a challenging problem that has a high relevance for several human-computer interaction applications, including AR/VR, robotics, or sign language recognition. Existing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::241384adeff3ab3fdb53622f6033e2fc
Publikováno v:
ACM Transactions on Graphics
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=r3c4b2081b22::dd2bf6960592ef0f2ac2da7cf49f4f27
Publikováno v:
ACM Transactions on Graphics
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=r3c4b2081b22::241384adeff3ab3fdb53622f6033e2fc
Autor:
Oleksandr Sotnychenko, Christian Theobalt, Weipeng Xu, Srinath Sridhar, Gerard Pons-Moll, Dushyant Mehta, Franziska Mueller
Publikováno v:
3DV
We propose a new single-shot method for multi-person 3D pose estimation in general scenes from a monocular RGB camera. Our approach uses novel occlusion-robust pose-maps (ORPM) which enable full body pose inference even under strong partial occlusion
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::321768bc6ad8e678f8ce76ff88c7a77a
https://doi.org/10.1109/3dv.2018.00024
https://doi.org/10.1109/3dv.2018.00024
Autor:
Hans-Peter Seidel, Dan Casas, Helge Rhodin, Oleksandr Sotnychenko, Christian Theobalt, Srinath Sridhar, Mohammad Shafiei, Weipeng Xu, Dushyant Mehta
We present the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera. Our method combines a new convolutional neural network (CNN) based pose regressor with k
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b6c8a0b711d14a157ed500c1a2923423
http://arxiv.org/abs/1705.01583
http://arxiv.org/abs/1705.01583
Autor:
Franziska Mueller, Christian Theobalt, Srinath Sridhar, Oleksandr Sotnychenko, Dan Casas, Dushyant Mehta
Publikováno v:
2017 IEEE International Conference on Computer Vision (ICCV)
We present an approach for real-time, robust and accurate hand pose estimation from moving egocentric RGB-D cameras in cluttered real environments. Existing methods typically fail for hand-object interactions in cluttered scenes imaged from egocentri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::00fe18842e3f2150127850b4dec9abe1
Autor:
Christian Theobalt, Florian Bernard, Oleksandr Sotnychenko, Srinath Sridhar, Dan Casas, Dushyant Mehta, Franziska Mueller
Publikováno v:
CVPR
We address the highly challenging problem of real-time 3D hand tracking based on a monocular RGB-only sequence. Our tracking method combines a convolutional neural network with a kinematic 3D hand model, such that it generalizes well to unseen data,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::56087ec51c7aa99ebe26c45302c3e2c8
Autor:
Helge Rhodin, Christian Theobalt, Dan Casas, Dushyant Mehta, Pascal Fua, Weipeng Xu, Oleksandr Sotnychenko
Publikováno v:
2017 International Conference on 3D Vision (3DV)
3DV
3DV
We propose a CNN-based approach for 3D human body pose estimation from single RGB images that addresses the issue of limited generalizability of models trained solely on the starkly limited publicly available 3D pose data. Using only the existing 3D
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::32803e9a8f1cf9aabd94005a4e6e156f
http://arxiv.org/abs/1611.09813
http://arxiv.org/abs/1611.09813
Autor:
Weipeng Xu, Helge Rhodin, Franziska Mueller, Pascal Fua, Christian Theobalt, Mohamed Elgharib, Dushyant Mehta, Gerard Pons-Moll, Oleksandr Sotnychenko, Hans-Peter Seidel
We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions by objects and by other people. Our method operates in subsequent sta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dd2bf6960592ef0f2ac2da7cf49f4f27
https://infoscience.epfl.ch/record/282223
https://infoscience.epfl.ch/record/282223