FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2014872288> ?p ?o ?g. }

• W2014872288 abstract "The availability of 3D hardware has so far outpaced the production of 3D content. Although to date many methods have been proposed to convert 2D images to 3D stereopairs, the most successful ones involve human operators and, therefore, are time-consuming and costly, while the fully-automatic ones have not yet achieved the same level of quality. This subpar performance is due to the fact that automatic methods usually rely on assumptions about the captured 3D scene that are often violated in practice. In this paper, we explore a radically different approach inspired by our work on saliency detection in images. Instead of relying on a deterministic scene model for the input 2D image, we propose to learn the model from a large dictionary of stereopairs, such as YouTube 3D. Our new approach is built upon a key observation and an assumption. The key observation is that among millions of stereopairs available on-line, there likely exist many stereopairs whose 3D content matches that of the 2D input (query). We assume that two stereopairs whose left images are photometrically similar are likely to have similar disparity fields. Our approach first finds a number of on-line stereopairs whose left image is a close photometric match to the 2D query and then extracts depth information from these stereopairs. Since disparities for the selected stereopairs differ due to differences in underlying image content, level of noise, distortions, etc., we combine them by using the median. We apply the resulting median disparity field to the 2D query to obtain the corresponding right image, while handling occlusions and newly-exposed areas in the usual way. We have applied our method in two scenarios. First, we used YouTube 3D videos in search of the most similar frames. Then, we repeated the experiments on a small, but carefully-selected, dictionary of stereopairs closely matching the query. This, to a degree, emulates the results one would expect from the use of an extremely large 3D repository. While far from perfect, the presented results demonstrate that on-line repositories of 3D content can be used for effective 2D-to-3D image conversion. With the continuously increasing amount of 3D data on-line and with the rapidly growing computing power in the cloud, the proposed framework seems a promising alternative to operator-assisted 2D-to-3D conversion." @default.
• W2014872288 created "2016-06-24" @default.
• W2014872288 creator A5019150411 @default.
• W2014872288 creator A5024859042 @default.
• W2014872288 creator A5036913803 @default.
• W2014872288 creator A5045077650 @default.
• W2014872288 creator A5063199641 @default.
• W2014872288 creator A5079429599 @default.
• W2014872288 date "2012-02-09" @default.
• W2014872288 modified "2023-10-07" @default.
• W2014872288 title "Automatic 2D-to-3D image conversion using 3D examples from the internet" @default.
• W2014872288 doi "https://doi.org/10.1117/12.910601" @default.
• W2014872288 hasPublicationYear "2012" @default.
• W2014872288 type Work @default.
• W2014872288 sameAs 2014872288 @default.
• W2014872288 citedByCount "34" @default.
• W2014872288 countsByYear W20148722882012 @default.
• W2014872288 countsByYear W20148722882013 @default.
• W2014872288 countsByYear W20148722882014 @default.
• W2014872288 countsByYear W20148722882015 @default.
• W2014872288 countsByYear W20148722882016 @default.
• W2014872288 countsByYear W20148722882018 @default.
• W2014872288 countsByYear W20148722882019 @default.
• W2014872288 countsByYear W20148722882022 @default.
• W2014872288 crossrefType "proceedings-article" @default.
• W2014872288 hasAuthorship W2014872288A5019150411 @default.
• W2014872288 hasAuthorship W2014872288A5024859042 @default.
• W2014872288 hasAuthorship W2014872288A5036913803 @default.
• W2014872288 hasAuthorship W2014872288A5045077650 @default.
• W2014872288 hasAuthorship W2014872288A5063199641 @default.
• W2014872288 hasAuthorship W2014872288A5079429599 @default.
• W2014872288 hasConcept C110875604 @default.
• W2014872288 hasConcept C115961682 @default.
• W2014872288 hasConcept C136764020 @default.
• W2014872288 hasConcept C154945302 @default.
• W2014872288 hasConcept C198352243 @default.
• W2014872288 hasConcept C202444582 @default.
• W2014872288 hasConcept C2524010 @default.
• W2014872288 hasConcept C26517878 @default.
• W2014872288 hasConcept C31972630 @default.
• W2014872288 hasConcept C33923547 @default.
• W2014872288 hasConcept C38652104 @default.
• W2014872288 hasConcept C41008148 @default.
• W2014872288 hasConcept C84824328 @default.
• W2014872288 hasConcept C9652623 @default.
• W2014872288 hasConcept C99498987 @default.
• W2014872288 hasConceptScore W2014872288C110875604 @default.
• W2014872288 hasConceptScore W2014872288C115961682 @default.
• W2014872288 hasConceptScore W2014872288C136764020 @default.
• W2014872288 hasConceptScore W2014872288C154945302 @default.
• W2014872288 hasConceptScore W2014872288C198352243 @default.
• W2014872288 hasConceptScore W2014872288C202444582 @default.
• W2014872288 hasConceptScore W2014872288C2524010 @default.
• W2014872288 hasConceptScore W2014872288C26517878 @default.
• W2014872288 hasConceptScore W2014872288C31972630 @default.
• W2014872288 hasConceptScore W2014872288C33923547 @default.
• W2014872288 hasConceptScore W2014872288C38652104 @default.
• W2014872288 hasConceptScore W2014872288C41008148 @default.
• W2014872288 hasConceptScore W2014872288C84824328 @default.
• W2014872288 hasConceptScore W2014872288C9652623 @default.
• W2014872288 hasConceptScore W2014872288C99498987 @default.
• W2014872288 hasLocation W20148722881 @default.
• W2014872288 hasOpenAccess W2014872288 @default.
• W2014872288 hasPrimaryLocation W20148722881 @default.
• W2014872288 hasRelatedWork W2003340466 @default.
• W2014872288 hasRelatedWork W2075263707 @default.
• W2014872288 hasRelatedWork W2083961718 @default.
• W2014872288 hasRelatedWork W2090087700 @default.
• W2014872288 hasRelatedWork W2130228941 @default.
• W2014872288 hasRelatedWork W2144655638 @default.
• W2014872288 hasRelatedWork W2158314067 @default.
• W2014872288 hasRelatedWork W2161229648 @default.
• W2014872288 hasRelatedWork W2415044327 @default.
• W2014872288 hasRelatedWork W2993674027 @default.
• W2014872288 isParatext "false" @default.
• W2014872288 isRetracted "false" @default.
• W2014872288 magId "2014872288" @default.
• W2014872288 workType "article" @default.