Matches in SemOpenAlex for { <https://semopenalex.org/work/W2095924849> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W2095924849 abstract "New-view synthesis (NVS) using texture priors (as opposed to surface-smoothness priors) can yield high quality results, but the standard formulation is in terms of large-clique Markov random fields (MRFs). Only local optimization methods such as iterated conditional modes, which are prone to fall into local minima close to the initial estimate, are practical for solving these problems. In this paper we replace the large-clique energies with pairwise potentials, by restricting the patch dictionary for each clique to image regions suitable for that clique. This enables for the first time the use of a global optimization method, such as tree-reweighted message passing, to solve the NVS problem with image-based priors. We employ a robust, truncated quadratic kernel to reject outliers caused by occlusions, specularities and moving objects, within our global optimization. Because the MRF optimization is thus fast, computing the unary potentials becomes the new performance bottleneck. An additional contribution of this paper is a novel, fast method for enumerating color modes of the per-pixel unary potentials, despite the non-convex nature of our robust kernel. We compare the results of our technique with other rendering methods, and discuss the relative merits and flaws of regularizing color, and of local versus global dictionaries." @default.
- W2095924849 created "2016-06-24" @default.
- W2095924849 creator A5000354478 @default.
- W2095924849 creator A5018851970 @default.
- W2095924849 creator A5068587315 @default.
- W2095924849 date "2007-06-01" @default.
- W2095924849 modified "2023-10-05" @default.
- W2095924849 title "Efficient new-view synthesis using pairwise dictionary priors" @default.
- W2095924849 cites W112500889 @default.
- W2095924849 cites W1857926807 @default.
- W2095924849 cites W1967577110 @default.
- W2095924849 cites W1998458472 @default.
- W2095924849 cites W1999360130 @default.
- W2095924849 cites W2033819227 @default.
- W2095924849 cites W2066763472 @default.
- W2095924849 cites W2067191022 @default.
- W2095924849 cites W2083518538 @default.
- W2095924849 cites W2101309634 @default.
- W2095924849 cites W2116013899 @default.
- W2095924849 cites W2127108679 @default.
- W2095924849 cites W2131686571 @default.
- W2095924849 cites W2139643804 @default.
- W2095924849 cites W2143516773 @default.
- W2095924849 cites W2146914716 @default.
- W2095924849 cites W2149760002 @default.
- W2095924849 cites W2158162781 @default.
- W2095924849 cites W2164918853 @default.
- W2095924849 cites W2110942492 @default.
- W2095924849 doi "https://doi.org/10.1109/cvpr.2007.383077" @default.
- W2095924849 hasPublicationYear "2007" @default.
- W2095924849 type Work @default.
- W2095924849 sameAs 2095924849 @default.
- W2095924849 citedByCount "14" @default.
- W2095924849 countsByYear W20959248492019 @default.
- W2095924849 countsByYear W20959248492020 @default.
- W2095924849 crossrefType "proceedings-article" @default.
- W2095924849 hasAuthorship W2095924849A5000354478 @default.
- W2095924849 hasAuthorship W2095924849A5018851970 @default.
- W2095924849 hasAuthorship W2095924849A5068587315 @default.
- W2095924849 hasConcept C107673813 @default.
- W2095924849 hasConcept C154945302 @default.
- W2095924849 hasConcept C177769412 @default.
- W2095924849 hasConcept C184898388 @default.
- W2095924849 hasConcept C204321447 @default.
- W2095924849 hasConcept C41008148 @default.
- W2095924849 hasConceptScore W2095924849C107673813 @default.
- W2095924849 hasConceptScore W2095924849C154945302 @default.
- W2095924849 hasConceptScore W2095924849C177769412 @default.
- W2095924849 hasConceptScore W2095924849C184898388 @default.
- W2095924849 hasConceptScore W2095924849C204321447 @default.
- W2095924849 hasConceptScore W2095924849C41008148 @default.
- W2095924849 hasLocation W20959248491 @default.
- W2095924849 hasOpenAccess W2095924849 @default.
- W2095924849 hasPrimaryLocation W20959248491 @default.
- W2095924849 hasRelatedWork W2029790457 @default.
- W2095924849 hasRelatedWork W2487162673 @default.
- W2095924849 hasRelatedWork W2580650124 @default.
- W2095924849 hasRelatedWork W2748952813 @default.
- W2095924849 hasRelatedWork W2899084033 @default.
- W2095924849 hasRelatedWork W2968424575 @default.
- W2095924849 hasRelatedWork W3122088529 @default.
- W2095924849 hasRelatedWork W3142333283 @default.
- W2095924849 hasRelatedWork W3192589309 @default.
- W2095924849 hasRelatedWork W4386190339 @default.
- W2095924849 isParatext "false" @default.
- W2095924849 isRetracted "false" @default.
- W2095924849 magId "2095924849" @default.
- W2095924849 workType "article" @default.