Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Jörg Hendrik Kappes"'
Publikováno v:
IEEE Transactions on Computational Imaging. 2:335-347
We study an energy formulation for non-binary discrete tomography and introduce a non-convex coupling term in order to combine discrete constraints with a continuous reconstruction method based on total variation regularization. The optimization is c
Publikováno v:
Computer Vision and Image Understanding. 143:104-119
We propose a novel and general formulation for hyper-graph correlation clustering.Any permutation invariant function can be included into a multicut problem.We provide a comparison of LP and ILP cutting plane methods and rounding procedures for the m
We present a probabilistic graphical model formulation for the graph clustering problem. This enables us to locally represent uncertainty of image partitions by approximate marginal distributions in a mathematically substantiated way, and to rectify
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ffe16de5ce53f29692b390b261f6ae7b
http://arxiv.org/abs/1601.02088
http://arxiv.org/abs/1601.02088
Publikováno v:
International Journal of Computer Vision. 87:93-117
Object detection is one of the key components in modern computer vision systems. While the detection of a specific rigid object under changing viewpoints was considered hard just a few years ago, current research strives to detect and recognize class
Autor:
Bogdan Savchynskyy, Paul Swoboda, Jörg Hendrik Kappes, Christoph Schnörr, Alexander Shekhovtsov
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 38(7)
We consider the energy minimization problem for undirected graphical models, also known as MAP-inference problem for Markov random fields which is NP-hard in general. We propose a novel polynomial time algorithm to obtain a part of its optimal non-re
Publikováno v:
CVPR
Correlation clustering, or multicut partitioning, is widely used in image segmentation for partitioning an undirected graph or image with positive and negative edge weights such that the sum of cut edge weights is minimized. Due to its NP-hardness, e
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319249469
GCPR
GCPR
We present an iterative reconstruction algorithm for binary tomography, called TomoGC, that solves the reconstruction problem based on a constrained graphical model by a sequence of graphcuts. TomoGC reconstructs objects even if a low number of measu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aece27e4e08211455c0830621ab63928
https://doi.org/10.1007/978-3-319-24947-6_21
https://doi.org/10.1007/978-3-319-24947-6_21
Autor:
Jan Lellmann, Jörg Hendrik Kappes, Carsten Rother, Bogdan Savchynskyy, Bernhard X. Kausler, Nikos Komodakis, Bjoern Andres, Christoph Schnörr, Thorben Kröger, Sungwoong Kim, Sebastian Nowozin, Fred A. Hamprecht, Dhruv Batra
Publikováno v:
International Journal of Computer Vision
International Journal of Computer Vision, Springer Verlag, 2015, ⟨10.1007/s11263-015-0809-x⟩
International Journal of Computer Vision, Springer Verlag, 2015, ⟨10.1007/s11263-015-0809-x⟩
International audience; Szeliski et al. published an influential study in 2006 on energy minimization methods for Markov Random Fields (MRF). This study provided valuable insights in choosing the best optimization technique for certain classes of pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3e8fa0c9cd131122c1b8dab3b4d1809
https://hal.archives-ouvertes.fr/hal-01247122/document
https://hal.archives-ouvertes.fr/hal-01247122/document
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319184609
SSVM
SSVM
We exploit recent progress on globally optimal MAP inference by integer programming and perturbation-based approximations of the log-partition function. This enables to locally represent uncertainty of image partitions by approximate marginal distrib
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b384b6c8d6da7ba87f36aa91b7e4e858
https://doi.org/10.1007/978-3-319-18461-6_19
https://doi.org/10.1007/978-3-319-18461-6_19
Publikováno v:
Computer Vision-ECCV 2014 Workshops ISBN: 9783319161808
ECCV Workshops (2)
ECCV Workshops (2)
Many computer vision problems can be cast into optimization problems over discrete graphical models also known as Markov or conditional random fields. Standard methods are able to solve those problems quite efficiently. However, problems with huge la
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c16c67490c5480867da7e59d232f1ce6
https://doi.org/10.1007/978-3-319-16181-5_37
https://doi.org/10.1007/978-3-319-16181-5_37