Matches in SemOpenAlex for { <https://semopenalex.org/work/W2990187139> ?p ?o ?g. }
- W2990187139 abstract "Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene. It is challenging since it needs to separate one image into two components. To tackle this, conventional methods introduce various priors to constrain the solution, yet with limited performance. Meanwhile, the problem is typically solved by supervised learning methods, which is actually not an ideal solution since obtaining ground truth reflectance and shading for massive general natural scenes is challenging and even impossible. In this paper, we propose a novel unsupervised intrinsic image decomposition framework, which relies on neither labeled training data nor hand-crafted priors. Instead, it directly learns the latent feature of reflectance and shading from unsupervised and uncorrelated data. To enable this, we explore the independence between reflectance and shading, the domain invariant content constraint and the physical constraint. Extensive experiments on both synthetic and real image datasets demonstrate consistently superior performance of the proposed method." @default.
- W2990187139 created "2019-12-05" @default.
- W2990187139 creator A5003277535 @default.
- W2990187139 creator A5012200112 @default.
- W2990187139 creator A5024277884 @default.
- W2990187139 creator A5050933800 @default.
- W2990187139 date "2019-11-22" @default.
- W2990187139 modified "2023-09-26" @default.
- W2990187139 title "Unsupervised Learning for Intrinsic Image Decomposition from a Single Image" @default.
- W2990187139 cites W1513100184 @default.
- W2990187139 cites W1934235358 @default.
- W2990187139 cites W1980212291 @default.
- W2990187139 cites W1982762150 @default.
- W2990187139 cites W2010812559 @default.
- W2990187139 cites W2027560260 @default.
- W2990187139 cites W2076491823 @default.
- W2990187139 cites W2080794127 @default.
- W2990187139 cites W2113404166 @default.
- W2990187139 cites W2119523460 @default.
- W2990187139 cites W2125893760 @default.
- W2990187139 cites W2164847484 @default.
- W2990187139 cites W2190691619 @default.
- W2990187139 cites W2193045528 @default.
- W2990187139 cites W2194775991 @default.
- W2990187139 cites W2199820243 @default.
- W2990187139 cites W2502312327 @default.
- W2990187139 cites W2576378358 @default.
- W2990187139 cites W2593414223 @default.
- W2990187139 cites W2603777577 @default.
- W2990187139 cites W2888277922 @default.
- W2990187139 cites W2895013824 @default.
- W2990187139 cites W2945542907 @default.
- W2990187139 cites W2952972288 @default.
- W2990187139 cites W2954058873 @default.
- W2990187139 cites W2962793481 @default.
- W2990187139 cites W2962947361 @default.
- W2990187139 cites W2963073614 @default.
- W2990187139 cites W2963587818 @default.
- W2990187139 cites W2963644875 @default.
- W2990187139 cites W2963800363 @default.
- W2990187139 cites W2963890275 @default.
- W2990187139 cites W2964321964 @default.
- W2990187139 cites W2965041861 @default.
- W2990187139 cites W2985810937 @default.
- W2990187139 cites W2998637570 @default.
- W2990187139 cites W3159890710 @default.
- W2990187139 cites W2990896888 @default.
- W2990187139 doi "https://doi.org/10.48550/arxiv.1911.09930" @default.
- W2990187139 hasPublicationYear "2019" @default.
- W2990187139 type Work @default.
- W2990187139 sameAs 2990187139 @default.
- W2990187139 citedByCount "0" @default.
- W2990187139 crossrefType "posted-content" @default.
- W2990187139 hasAuthorship W2990187139A5003277535 @default.
- W2990187139 hasAuthorship W2990187139A5012200112 @default.
- W2990187139 hasAuthorship W2990187139A5024277884 @default.
- W2990187139 hasAuthorship W2990187139A5050933800 @default.
- W2990187139 hasBestOaLocation W29901871391 @default.
- W2990187139 hasConcept C107673813 @default.
- W2990187139 hasConcept C115961682 @default.
- W2990187139 hasConcept C121684516 @default.
- W2990187139 hasConcept C138885662 @default.
- W2990187139 hasConcept C153180895 @default.
- W2990187139 hasConcept C154945302 @default.
- W2990187139 hasConcept C177515723 @default.
- W2990187139 hasConcept C177769412 @default.
- W2990187139 hasConcept C2524010 @default.
- W2990187139 hasConcept C2776036281 @default.
- W2990187139 hasConcept C2776401178 @default.
- W2990187139 hasConcept C31972630 @default.
- W2990187139 hasConcept C33923547 @default.
- W2990187139 hasConcept C41008148 @default.
- W2990187139 hasConcept C41895202 @default.
- W2990187139 hasConcept C8038995 @default.
- W2990187139 hasConceptScore W2990187139C107673813 @default.
- W2990187139 hasConceptScore W2990187139C115961682 @default.
- W2990187139 hasConceptScore W2990187139C121684516 @default.
- W2990187139 hasConceptScore W2990187139C138885662 @default.
- W2990187139 hasConceptScore W2990187139C153180895 @default.
- W2990187139 hasConceptScore W2990187139C154945302 @default.
- W2990187139 hasConceptScore W2990187139C177515723 @default.
- W2990187139 hasConceptScore W2990187139C177769412 @default.
- W2990187139 hasConceptScore W2990187139C2524010 @default.
- W2990187139 hasConceptScore W2990187139C2776036281 @default.
- W2990187139 hasConceptScore W2990187139C2776401178 @default.
- W2990187139 hasConceptScore W2990187139C31972630 @default.
- W2990187139 hasConceptScore W2990187139C33923547 @default.
- W2990187139 hasConceptScore W2990187139C41008148 @default.
- W2990187139 hasConceptScore W2990187139C41895202 @default.
- W2990187139 hasConceptScore W2990187139C8038995 @default.
- W2990187139 hasLocation W29901871391 @default.
- W2990187139 hasOpenAccess W2990187139 @default.
- W2990187139 hasPrimaryLocation W29901871391 @default.
- W2990187139 hasRelatedWork W1504288058 @default.
- W2990187139 hasRelatedWork W2048505601 @default.
- W2990187139 hasRelatedWork W2102575890 @default.
- W2990187139 hasRelatedWork W2116675934 @default.
- W2990187139 hasRelatedWork W2167293474 @default.
- W2990187139 hasRelatedWork W2331674254 @default.
- W2990187139 hasRelatedWork W2401036251 @default.