Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Vijay Badrinarayanan"'
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585884
ECCV (21)
ECCV (21)
Multi-view stereo (MVS) is the golden mean between the accuracy of active depth sensing and the practicality of monocular depth estimation. Cost volume based approaches employing 3D convolutional neural networks (CNNs) have considerably improved the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::56b0e5660c87aed9997729a06c2fbac2
https://doi.org/10.1007/978-3-030-58589-1_7
https://doi.org/10.1007/978-3-030-58589-1_7
Autor:
Zak Murez, Tarrence van As, James Bartolozzi, Vijay Badrinarayanan, Andrew Rabinovich, Ayan Sinha
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585709
ECCV (7)
ECCV (7)
We present an end-to-end 3D reconstruction method for a scene by directly regressing a truncated signed distance function (TSDF) from a set of posed RGB images. Traditional approaches to 3D reconstruction rely on an intermediate representation of dep
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bba523fde6ef704ea466220b21334e7f
https://doi.org/10.1007/978-3-030-58571-6_25
https://doi.org/10.1007/978-3-030-58571-6_25
Publikováno v:
ICCV Workshops
Eye gaze estimation is a crucial component in Virtual and Mixed Reality. In head-mounted VR/MR devices the eyes are imaged off-axis to avoid blocking the user's gaze, this view-point makes drawing eye related inferences very challenging. In this work
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1e4ca3e4741325df611f03c08a583bc3
https://doi.org/10.1109/iccvw.2019.00455
https://doi.org/10.1109/iccvw.2019.00455
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012243
ECCV (4)
ECCV (4)
We present a deep model that can accurately produce dense depth maps given an RGB image with known depth at a very sparse set of pixels. The model works simultaneously for both indoor/outdoor scenes and produces state-of-the-art dense depth maps at n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::79884d023669860d88d4efd4281a5b91
https://doi.org/10.1007/978-3-030-01225-0_11
https://doi.org/10.1007/978-3-030-01225-0_11
Publikováno v:
ICCV
This paper focuses on the task of room layout estimation from a monocular RGB image. Prior works break the problem into two sub-tasks: semantic segmentation of floor, walls, ceiling to produce layout hypotheses, followed by an iterative optimization
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a979e0158419f4a0c5222ba0f40811ed
https://doi.org/10.1109/iccv.2017.521
https://doi.org/10.1109/iccv.2017.521
Publikováno v:
International Journal of Computer Vision. 110:14-29
We present a novel mixture of trees probabilistic graphical model for semi-supervised video segmentation. Each component in this mixture represents a tree structured temporal linkage between super-pixels from the first to the last frame of a video se
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c48da293525dcc0f1fa6e1de4509c25e
https://doi.org/10.1007/s11263-013-0673-5
https://doi.org/10.1007/s11263-013-0673-5
Autor:
Jigna Chandaria, Gianfranco Nencioni, Dmytro Karamshuk, Vijay Badrinarayanan, Nishanth Sastry, Gareth Tyson, Jon Crowcroft
Publikováno v:
Nencioni, G, Sastry, N, Tyson, G, Badrinarayanan, V, Karamshuk, D, Chandaria, J & Crowcroft, J 2016, ' SCORE : Exploiting Global Broadcasts to Create Offline Personal Channels for On-Demand Access ', Ieee-Acm Transactions On Networking, vol. 24, no. 4, 7210228, pp. 2429-2442 . https://doi.org/10.1109/TNET.2015.2456186
IEEE/ACM Transactions on Networking
IEEE/ACM Transactions on Networking
The last 5 years have seen a dramatic shift in media distribution. For decades, TV and radio were solely provisioned using push-based broadcast technologies, forcing people to adhere to fixed schedules. The introduction of catch-up services, however,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::088ebd6bbde662ef910551e7fc73ed08
https://www.repository.cam.ac.uk/handle/1810/284900
https://www.repository.cam.ac.uk/handle/1810/284900
Publikováno v:
CVPR
Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments. Recent attempts with supervised learning have shown promise in this direction but also highlighted the need for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c2570c2010db9420fb639b32f639c72d
https://doi.org/10.1109/cvpr.2016.442
https://doi.org/10.1109/cvpr.2016.442
We present a deep learning framework for probabilistic pixel-wise semantic segmentation, which we term Bayesian SegNet. Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is essential for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9ff49d10acd8b2c790f40139d1d3f7b4
We present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an encoder network, a corresponding decoder network followed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::001266b87e6bc179e882af1725bd6b9a