FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089136067> ?p ?o ?g. }

• W3089136067 endingPage "2674" @default.
• W3089136067 startingPage "2661" @default.
• W3089136067 abstract "Intrinsic image analysis plays an important role for image understanding, since it can provide accurate reflectance, shape and illumination information of the scene. However, intrinsic image analysis is an ill-posed problem which need to apply extra constrains for the decomposition of reflectance image and shading image from a single image. Recently deep neural networks are introduced for intrinsic image analysis, which can produce two intrinsic components simultaneously. In fact, the mutually exclusive relationship between reflectance image and shading image is not only a constraint for decomposition but also can improve the decomposition results. However, this relationship is always omitted in the current networks. In order to address this problem, we propose a novel deep network called as Cascaded Quotient Network (CasQNet) for intrinsic image decomposition. The CasQNet consists of two sub-networks: a Pyramid Mini-U-Net (PyNet) that specifically extracts the reflectance image in multi-scale and a Shading Optimization Network (SoNet) that optimizes the resulting shading. These two sub-networks are cascaded by a quotient operation, which directly enforces the mutually exclusive relationship between reflectance image and shading image in the network architecture. In PyNet, the task of reconstructing reflectance image is achieved by a series of nested multi-scale U-Nets, which simplified the learning task for each U-Net. SoNet is designed to address the unsmooth and blur problems of extreme points caused by the quotient operation. PyNet and SoNet are trained alternately and finally jointed in cascaded structure. Furthermore, we combine multiple loss functions, which consist of data loss, correlation loss and reconstruction loss, for improving the learning effectiveness. To evaluate our proposed algorithm, extensive experiments are performed on three datasets, i.e., ShapeNet, BOLD Surface and MIT Intrinsic Image datasets. Qualitative and quantitative results show that our model achieves the best performance compared to the state-of-the-art methods." @default.
• W3089136067 created "2020-10-01" @default.
• W3089136067 creator A5001972993 @default.
• W3089136067 creator A5007583477 @default.
• W3089136067 creator A5020220235 @default.
• W3089136067 creator A5035883232 @default.
• W3089136067 creator A5056412615 @default.
• W3089136067 date "2021-07-01" @default.
• W3089136067 modified "2023-10-15" @default.
• W3089136067 title "CasQNet: Intrinsic Image Decomposition Based on Cascaded Quotient Network" @default.
• W3089136067 cites W1576148925 @default.
• W3089136067 cites W1934235358 @default.
• W3089136067 cites W2027560260 @default.
• W3089136067 cites W2076205488 @default.
• W3089136067 cites W2076491823 @default.
• W3089136067 cites W2082232962 @default.
• W3089136067 cites W2087257250 @default.
• W3089136067 cites W2091247382 @default.
• W3089136067 cites W2101856619 @default.
• W3089136067 cites W2113404166 @default.
• W3089136067 cites W2116233832 @default.
• W3089136067 cites W2116919352 @default.
• W3089136067 cites W2123785012 @default.
• W3089136067 cites W2123941108 @default.
• W3089136067 cites W2133665775 @default.
• W3089136067 cites W2136748901 @default.
• W3089136067 cites W2154423567 @default.
• W3089136067 cites W2157070558 @default.
• W3089136067 cites W2164847484 @default.
• W3089136067 cites W2193045528 @default.
• W3089136067 cites W2194775991 @default.
• W3089136067 cites W2199820243 @default.
• W3089136067 cites W2221366145 @default.
• W3089136067 cites W2567309586 @default.
• W3089136067 cites W2583983165 @default.
• W3089136067 cites W2780018032 @default.
• W3089136067 cites W2794766838 @default.
• W3089136067 cites W2798282242 @default.
• W3089136067 cites W2798966709 @default.
• W3089136067 cites W2895013824 @default.
• W3089136067 cites W2910832120 @default.
• W3089136067 cites W2963395931 @default.
• W3089136067 cites W2963587818 @default.
• W3089136067 cites W2964030969 @default.
• W3089136067 cites W2964040059 @default.
• W3089136067 cites W2964267765 @default.
• W3089136067 cites W2964606879 @default.
• W3089136067 cites W2985810937 @default.
• W3089136067 cites W3004814282 @default.
• W3089136067 cites W3046257495 @default.
• W3089136067 cites W3080756971 @default.
• W3089136067 cites W3099762460 @default.
• W3089136067 cites W4214948749 @default.
• W3089136067 doi "https://doi.org/10.1109/tcsvt.2020.3024687" @default.
• W3089136067 hasPublicationYear "2021" @default.
• W3089136067 type Work @default.
• W3089136067 sameAs 3089136067 @default.
• W3089136067 citedByCount "4" @default.
• W3089136067 countsByYear W30891360672022 @default.
• W3089136067 countsByYear W30891360672023 @default.
• W3089136067 crossrefType "journal-article" @default.
• W3089136067 hasAuthorship W3089136067A5001972993 @default.
• W3089136067 hasAuthorship W3089136067A5007583477 @default.
• W3089136067 hasAuthorship W3089136067A5020220235 @default.
• W3089136067 hasAuthorship W3089136067A5035883232 @default.
• W3089136067 hasAuthorship W3089136067A5056412615 @default.
• W3089136067 hasConcept C114614502 @default.
• W3089136067 hasConcept C115961682 @default.
• W3089136067 hasConcept C124681953 @default.
• W3089136067 hasConcept C154945302 @default.
• W3089136067 hasConcept C18903297 @default.
• W3089136067 hasConcept C199422724 @default.
• W3089136067 hasConcept C31972630 @default.
• W3089136067 hasConcept C33923547 @default.
• W3089136067 hasConcept C41008148 @default.
• W3089136067 hasConcept C86803240 @default.
• W3089136067 hasConcept C9417928 @default.
• W3089136067 hasConceptScore W3089136067C114614502 @default.
• W3089136067 hasConceptScore W3089136067C115961682 @default.
• W3089136067 hasConceptScore W3089136067C124681953 @default.
• W3089136067 hasConceptScore W3089136067C154945302 @default.
• W3089136067 hasConceptScore W3089136067C18903297 @default.
• W3089136067 hasConceptScore W3089136067C199422724 @default.
• W3089136067 hasConceptScore W3089136067C31972630 @default.
• W3089136067 hasConceptScore W3089136067C33923547 @default.
• W3089136067 hasConceptScore W3089136067C41008148 @default.
• W3089136067 hasConceptScore W3089136067C86803240 @default.
• W3089136067 hasConceptScore W3089136067C9417928 @default.
• W3089136067 hasFunder F4320321001 @default.
• W3089136067 hasIssue "7" @default.
• W3089136067 hasLocation W30891360671 @default.
• W3089136067 hasOpenAccess W3089136067 @default.
• W3089136067 hasPrimaryLocation W30891360671 @default.
• W3089136067 hasRelatedWork W2005185696 @default.
• W3089136067 hasRelatedWork W2080322084 @default.
• W3089136067 hasRelatedWork W2161229648 @default.
• W3089136067 hasRelatedWork W2235753890 @default.
• W3089136067 hasRelatedWork W23451984 @default.

• next