Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Armin Mustafa"'
Publikováno v:
International Journal of Computer Vision. 130:1583-1606
We introduce the first approach to solve the challenging problem of automatic 4D visual scene understanding for complex dynamic scenes with multiple interacting people from multi-view video. Our approach simultaneously estimates a detailed model that
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::13b48ac0a44623d639e045b30b4176c6
https://doi.org/10.1007/s11263-022-01599-4
https://doi.org/10.1007/s11263-022-01599-4
Publikováno v:
2022 International Conference on 3D Vision (3DV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a2b3ddfee4f0fa9ae85ce772c9bdbc12
https://doi.org/10.1109/3dv57658.2022.00031
https://doi.org/10.1109/3dv57658.2022.00031
Autor:
Adrian Hilton, Armin Mustafa
Publikováno v:
International Journal of Computer Vision. 128:319-335
Simultaneous semantically coherent object-based long-term 4D scene flow estimation, co-segmentation and reconstruction is proposed exploiting the coherence in semantic class labels both spatially, between views at a single time instant, and temporall
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6de499915a053d5ae9fe8fad28394840
https://doi.org/10.1007/s11263-019-01241-w
https://doi.org/10.1007/s11263-019-01241-w
Publikováno v:
CVPR
We present a new end-to-end learning framework to obtain detailed and spatially coherent reconstructions of multiple people from a single image. Existing multi-person methods suffer from two main drawbacks: they are often model-based and therefore ca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6229d840318b2122ad8f5c2a5544a7ec
http://arxiv.org/abs/2104.09283
http://arxiv.org/abs/2104.09283
Publikováno v:
CVPR Workshops
We present a novel method to learn temporally consistent 3D reconstruction of clothed people from a monocular video. Recent methods for 3D human reconstruction from monocular video using volumetric, implicit or parametric human shape models, produce
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::47d18423269fd3515259ea129072be72
Publikováno v:
Computer Vision – ACCV 2020 ISBN: 9783030695248
ACCV (1)
ACCV (1)
We present a novel method to improve the accuracy of the 3D reconstruction of clothed human shape from a single image. Recent work has introduced volumetric, implicit and model-based shape learning frameworks for reconstruction of objects and people
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bfc087ee7b27edc9eefe7af37c5a6e67
https://doi.org/10.1007/978-3-030-69525-5_5
https://doi.org/10.1007/978-3-030-69525-5_5
Existing techniques for dynamic scene reconstruction from multiple wide-baseline cameras primarily focus on reconstruction in controlled environments, with fixed calibrated cameras and strong prior constraints. This paper introduces a general approac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a437e83554255d91d7a4b3f42152ed4
https://eprints.soton.ac.uk/445057/
https://eprints.soton.ac.uk/445057/
Publikováno v:
Real VR – Immersive Digital Reality ISBN: 9783030418151
Real VR
Real VR
Light field video for content production is gaining both research and commercial interest as it has the potential to push the level of immersion for augmented and virtual reality to a close-to-reality experience. Light fields densely sample the viewi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::56e3522987d558b9048fd610d831c1fd
https://doi.org/10.1007/978-3-030-41816-8_2
https://doi.org/10.1007/978-3-030-41816-8_2
Publikováno v:
ICCV Workshops
Existing methods for stereo work on narrow baseline image pairs giving limited performance between wide baseline views. This paper proposes a framework to learn and estimate dense stereo for people from wide baseline image pairs. A synthetic people s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2bae2807cd9de1ebea89c3440e2d298b
https://doi.org/10.1109/iccvw.2019.00271
https://doi.org/10.1109/iccvw.2019.00271
Publikováno v:
3DV
Light fields are becoming an increasingly popular method of digital content production for visual effects and virtual/augmented reality as they capture a view dependent representation enabling photo realistic rendering over a range of viewpoints. Lig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::14248060a91ed80d9d7fe6ed1256dac1
https://doi.org/10.1109/3dv.2019.00060
https://doi.org/10.1109/3dv.2019.00060