FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2775678896> ?p ?o ?g. }

• W2775678896 abstract "Most digital camera pipelines use color constancy methods to reduce the influence of illumination and camera sensor on the colors of scene objects. The highest accuracy of color correction is obtained with learning-based color constancy methods, but they require a significant amount of calibrated training images with known ground-truth illumination. Such calibration is time consuming, preferably done for each sensor individually, and therefore a major bottleneck in acquiring high color constancy accuracy. Statistics-based methods do not require calibrated training images, but they are less accurate. In this paper an unsupervised learning-based method is proposed that learns its parameter values after approximating the unknown ground-truth illumination of the training images, thus avoiding calibration. In terms of accuracy the proposed method outperforms all statistics-based and many learning-based methods. An extension of the method is also proposed, which learns the needed parameters from non-calibrated images taken with one sensors and which can then be successfully applied to images taken with another sensor. This effectively enables inter-camera unsupervised learning for color constancy. Additionally, a new high quality color constancy benchmark dataset with 1365 calibrated images is created, used for testing, and made publicly available. The results are presented and discussed. The source code and the dataset are available at this http URL" @default.
• W2775678896 created "2017-12-22" @default.
• W2775678896 creator A5047540566 @default.
• W2775678896 creator A5053645603 @default.
• W2775678896 date "2017-12-01" @default.
• W2775678896 modified "2023-09-27" @default.
• W2775678896 title "Unsupervised Learning for Color Constancy" @default.
• W2775678896 cites W1530411632 @default.
• W2775678896 cites W1534426948 @default.
• W2775678896 cites W1673310716 @default.
• W2775678896 cites W1894971994 @default.
• W2775678896 cites W1898616786 @default.
• W2775678896 cites W1925897490 @default.
• W2775678896 cites W1960752652 @default.
• W2775678896 cites W1966855663 @default.
• W2775678896 cites W1967839231 @default.
• W2775678896 cites W1970141893 @default.
• W2775678896 cites W1988091178 @default.
• W2775678896 cites W2001541757 @default.
• W2775678896 cites W2012602905 @default.
• W2775678896 cites W2048520392 @default.
• W2775678896 cites W2052090926 @default.
• W2775678896 cites W2053354349 @default.
• W2775678896 cites W2059511298 @default.
• W2775678896 cites W2073060282 @default.
• W2775678896 cites W2076205488 @default.
• W2775678896 cites W2082538584 @default.
• W2775678896 cites W2083900019 @default.
• W2775678896 cites W2088828956 @default.
• W2775678896 cites W2099106464 @default.
• W2775678896 cites W2100001370 @default.
• W2775678896 cites W2107558608 @default.
• W2775678896 cites W2108303106 @default.
• W2775678896 cites W2111963040 @default.
• W2775678896 cites W2115257219 @default.
• W2775678896 cites W2116278081 @default.
• W2775678896 cites W2127701282 @default.
• W2775678896 cites W2128059302 @default.
• W2775678896 cites W2146745213 @default.
• W2775678896 cites W2154264220 @default.
• W2775678896 cites W2162210331 @default.
• W2775678896 cites W2171773573 @default.
• W2775678896 cites W22090881 @default.
• W2775678896 cites W2239332732 @default.
• W2775678896 cites W2241236399 @default.
• W2775678896 cites W2287042286 @default.
• W2775678896 cites W2396922686 @default.
• W2775678896 cites W2397711071 @default.
• W2775678896 cites W2408602001 @default.
• W2775678896 cites W2460242234 @default.
• W2775678896 cites W2464894273 @default.
• W2775678896 cites W2466285044 @default.
• W2775678896 cites W2472745537 @default.
• W2775678896 cites W2476974423 @default.
• W2775678896 cites W2509601486 @default.
• W2775678896 cites W2511760322 @default.
• W2775678896 cites W2519060067 @default.
• W2775678896 cites W2556952061 @default.
• W2775678896 cites W2561906970 @default.
• W2775678896 cites W2739489527 @default.
• W2775678896 cites W2756472722 @default.
• W2775678896 cites W2773987474 @default.
• W2775678896 cites W2781314508 @default.
• W2775678896 cites W2792812191 @default.
• W2775678896 cites W2793336811 @default.
• W2775678896 cites W2962679394 @default.
• W2775678896 cites W2963009255 @default.
• W2775678896 cites W2964100365 @default.
• W2775678896 cites W3099762460 @default.
• W2775678896 cites W608314793 @default.
• W2775678896 cites W759139936 @default.
• W2775678896 hasPublicationYear "2017" @default.
• W2775678896 type Work @default.
• W2775678896 sameAs 2775678896 @default.
• W2775678896 citedByCount "13" @default.
• W2775678896 countsByYear W27756788962018 @default.
• W2775678896 countsByYear W27756788962019 @default.
• W2775678896 countsByYear W27756788962020 @default.
• W2775678896 crossrefType "posted-content" @default.
• W2775678896 hasAuthorship W2775678896A5047540566 @default.
• W2775678896 hasAuthorship W2775678896A5053645603 @default.
• W2775678896 hasConcept C105795698 @default.
• W2775678896 hasConcept C115961682 @default.
• W2775678896 hasConcept C13280743 @default.
• W2775678896 hasConcept C142616399 @default.
• W2775678896 hasConcept C146849305 @default.
• W2775678896 hasConcept C153180895 @default.
• W2775678896 hasConcept C154945302 @default.
• W2775678896 hasConcept C159784718 @default.
• W2775678896 hasConcept C165838908 @default.
• W2775678896 hasConcept C185798385 @default.
• W2775678896 hasConcept C187888035 @default.
• W2775678896 hasConcept C205649164 @default.
• W2775678896 hasConcept C31972630 @default.
• W2775678896 hasConcept C33923547 @default.
• W2775678896 hasConcept C41008148 @default.
• W2775678896 hasConcept C9417928 @default.
• W2775678896 hasConceptScore W2775678896C105795698 @default.
• W2775678896 hasConceptScore W2775678896C115961682 @default.
• W2775678896 hasConceptScore W2775678896C13280743 @default.

• next