Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Mohamed Souiai"'
Publikováno v:
SIAM Journal on Imaging Sciences. 10:1845-1877
We consider an unsupervised image segmentation problem---from figure-ground separation to multiregion partitioning---that consists of maximal distribution separation (in terms of mutual information) with spatial regularity (total variation regulariza
Publikováno v:
RIUMA. Repositorio Institucional de la Universidad de Málaga
instname
3DV
instname
3DV
We propose a novel joint registration and segmentation approach to estimate scene flow from RGB-D images. Instead of assuming the scene to be composed of a number of independent rigidly-moving parts, we use non-binary labels to capture non-rigid defo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c7d914194f99665f7c5968ac78878f5c
http://hdl.handle.net/10630/10863
http://hdl.handle.net/10630/10863
Publikováno v:
ICCV
Despite their enormous success in solving hard combinatorial problems, convex relaxation approaches often suffer from the fact that the computed solutions are far from binary and that subsequent heuristic binarization may substantially degrade the qu
Publikováno v:
ICRA
RIUMA. Repositorio Institucional de la Universidad de Málaga
instname
RIUMA. Repositorio Institucional de la Universidad de Málaga
instname
This paper presents the first method to compute dense scene flow in real-time for RGB-D cameras. It is based on a variational formulation where brightness constancy and geometric consistency are imposed. Accounting for the depth data provided by RGB-
Publikováno v:
CVPR
We propose an optimization algorithm for mutual information-based unsupervised figure-ground separation. The algorithm jointly estimates the color distributions of the foreground and background, and separates them based on their mutual information wi
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319117515
GCPR
GCPR
We present an active learning framework for image segmentation with user interaction. Our system uses a sparse Gaussian Process classifier (GPC) trained on manually labeled image pixels (user scribbles) and refined in every active learning round. As
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::335894c2999879f5416b5f86dc602c30
https://doi.org/10.1007/978-3-319-11752-2_53
https://doi.org/10.1007/978-3-319-11752-2_53
Publikováno v:
ICCV Workshops
In this paper, we introduce the concept of proximity priors into semantic segmentation in order to discourage the presence of certain object classes (such as 'sheep' and 'wolf') 'in the vicinity' of each other. 'Vicinity' encompasses spatial distance
Publikováno v:
ICCV Workshops
In this paper we give a convex optimization approach for scene understanding. Since segmentation, object recognition and scene labeling strongly benefit from each other we propose to solve these tasks within a single convex optimization problem. In c
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783642406010
GCPR
GCPR
Convex relaxation techniques allow computing optimal or near-optimal solutions for a variety of multilabel problems in computer vision. Unfortunately, they are quite demanding in terms of memory and computation time making them unpractical for large-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::741bec799b066cea7cabecbb87a5dcc5
https://doi.org/10.1007/978-3-642-40602-7_20
https://doi.org/10.1007/978-3-642-40602-7_20
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783642403941
EMMCVPR
EMMCVPR
To obtain high-quality segmentation results the integration of semantic information is indispensable. In contrast to existing segmentation methods which use a spatial regularizer, i.e. a local interaction between image points, the co-occurrence prior
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::771c03f50d58cbd2b516264ad69536ee
https://doi.org/10.1007/978-3-642-40395-8_16
https://doi.org/10.1007/978-3-642-40395-8_16