FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210482106> ?p ?o ?g. }

• W3210482106 endingPage "9101" @default.
• W3210482106 startingPage "9088" @default.
• W3210482106 abstract "We propose a novel deep learning method for shadow removal. Inspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free image, the shadow parameters, and a matte layer. We use two deep networks, namely SP-Net and M-Net, to predict the shadow parameters and the shadow matte respectively. This system allows us to remove the shadow effects from images. We then employ an inpainting network, I-Net, to further refine the results. We train and test our framework on the most challenging shadow removal dataset (ISTD). Our method improves the state-of-the-art in terms of mean absolute error (MAE) for the shadow area by 20%. Furthermore, this decomposition allows us to formulate a patch-based weakly-supervised shadow removal method. This model can be trained without any shadow- free images (that are cumbersome to acquire) and achieves competitive shadow removal results compared to state-of-the-art methods that are trained with fully paired shadow and shadow-free images. Last, we introduce SBU-Timelapse, a video shadow removal dataset for evaluating shadow removal methods." @default.
• W3210482106 created "2021-11-08" @default.
• W3210482106 creator A5076307452 @default.
• W3210482106 creator A5084608346 @default.
• W3210482106 date "2022-12-01" @default.
• W3210482106 modified "2023-10-15" @default.
• W3210482106 title "Physics-Based Shadow Image Decomposition for Shadow Removal" @default.
• W3210482106 cites W1541667274 @default.
• W3210482106 cites W1566485861 @default.
• W3210482106 cites W1573546770 @default.
• W3210482106 cites W1590645542 @default.
• W3210482106 cites W1704999350 @default.
• W3210482106 cites W1884470205 @default.
• W3210482106 cites W1967913888 @default.
• W3210482106 cites W1978508694 @default.
• W3210482106 cites W1979504357 @default.
• W3210482106 cites W1997057955 @default.
• W3210482106 cites W1998270967 @default.
• W3210482106 cites W2003145026 @default.
• W3210482106 cites W2028240797 @default.
• W3210482106 cites W2035773017 @default.
• W3210482106 cites W2060850257 @default.
• W3210482106 cites W2073839959 @default.
• W3210482106 cites W2095761827 @default.
• W3210482106 cites W2122514671 @default.
• W3210482106 cites W2126173520 @default.
• W3210482106 cites W2141562793 @default.
• W3210482106 cites W2166502676 @default.
• W3210482106 cites W2300641502 @default.
• W3210482106 cites W2326925005 @default.
• W3210482106 cites W2412862597 @default.
• W3210482106 cites W2506817861 @default.
• W3210482106 cites W2519623608 @default.
• W3210482106 cites W2535388113 @default.
• W3210482106 cites W2549139847 @default.
• W3210482106 cites W2566793769 @default.
• W3210482106 cites W2605126331 @default.
• W3210482106 cites W2740832349 @default.
• W3210482106 cites W2765946592 @default.
• W3210482106 cites W2801375052 @default.
• W3210482106 cites W2884217841 @default.
• W3210482106 cites W2895126795 @default.
• W3210482106 cites W2943789680 @default.
• W3210482106 cites W2962793481 @default.
• W3210482106 cites W2963014378 @default.
• W3210482106 cites W2963073614 @default.
• W3210482106 cites W2963800363 @default.
• W3210482106 cites W2981771415 @default.
• W3210482106 cites W2997378071 @default.
• W3210482106 cites W2998154526 @default.
• W3210482106 cites W3035244041 @default.
• W3210482106 cites W3104943862 @default.
• W3210482106 cites W3108688141 @default.
• W3210482106 cites W3109116870 @default.
• W3210482106 cites W3201987584 @default.
• W3210482106 cites W4229783421 @default.
• W3210482106 doi "https://doi.org/10.1109/tpami.2021.3124934" @default.
• W3210482106 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34735336" @default.
• W3210482106 hasPublicationYear "2022" @default.
• W3210482106 type Work @default.
• W3210482106 sameAs 3210482106 @default.
• W3210482106 citedByCount "12" @default.
• W3210482106 countsByYear W32104821062022 @default.
• W3210482106 countsByYear W32104821062023 @default.
• W3210482106 crossrefType "journal-article" @default.
• W3210482106 hasAuthorship W3210482106A5076307452 @default.
• W3210482106 hasAuthorship W3210482106A5084608346 @default.
• W3210482106 hasBestOaLocation W32104821062 @default.
• W3210482106 hasConcept C115961682 @default.
• W3210482106 hasConcept C116544410 @default.
• W3210482106 hasConcept C11727466 @default.
• W3210482106 hasConcept C117797892 @default.
• W3210482106 hasConcept C154945302 @default.
• W3210482106 hasConcept C15744967 @default.
• W3210482106 hasConcept C31972630 @default.
• W3210482106 hasConcept C41008148 @default.
• W3210482106 hasConcept C542102704 @default.
• W3210482106 hasConceptScore W3210482106C115961682 @default.
• W3210482106 hasConceptScore W3210482106C116544410 @default.
• W3210482106 hasConceptScore W3210482106C11727466 @default.
• W3210482106 hasConceptScore W3210482106C117797892 @default.
• W3210482106 hasConceptScore W3210482106C154945302 @default.
• W3210482106 hasConceptScore W3210482106C15744967 @default.
• W3210482106 hasConceptScore W3210482106C31972630 @default.
• W3210482106 hasConceptScore W3210482106C41008148 @default.
• W3210482106 hasConceptScore W3210482106C542102704 @default.
• W3210482106 hasFunder F4320309480 @default.
• W3210482106 hasIssue "12" @default.
• W3210482106 hasLocation W32104821061 @default.
• W3210482106 hasLocation W32104821062 @default.
• W3210482106 hasLocation W32104821063 @default.
• W3210482106 hasLocation W32104821064 @default.
• W3210482106 hasOpenAccess W3210482106 @default.
• W3210482106 hasPrimaryLocation W32104821061 @default.
• W3210482106 hasRelatedWork W1574999717 @default.
• W3210482106 hasRelatedWork W166251047 @default.
• W3210482106 hasRelatedWork W2020564930 @default.
• W3210482106 hasRelatedWork W2059339452 @default.

• next