Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895983464> ?p ?o ?g. }
- W2895983464 endingPage "775" @default.
- W2895983464 startingPage "758" @default.
- W2895983464 abstract "Semi-Global Matching (SGM) uses an aggregation scheme to combine costs from multiple 1D scanline optimizations that tends to hurt its accuracy in difficult scenarios. We propose replacing this aggregation scheme with a new learning-based method that fuses disparity proposals estimated using scanline optimization. Our proposed SGM-Forest algorithm solves this problem using per-pixel classification. SGM-Forest currently ranks 1st on the ETH3D stereo benchmark and is ranked competitively on the Middlebury 2014 and KITTI 2015 benchmarks. It consistently outperforms SGM in challenging settings and under difficult training protocols that demonstrate robust generalization, while adding only a small computational overhead to SGM." @default.
- W2895983464 created "2018-10-26" @default.
- W2895983464 creator A5021908609 @default.
- W2895983464 creator A5071944294 @default.
- W2895983464 creator A5090341044 @default.
- W2895983464 date "2018-01-01" @default.
- W2895983464 modified "2023-10-18" @default.
- W2895983464 title "Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching" @default.
- W2895983464 cites W117717820 @default.
- W2895983464 cites W1557515246 @default.
- W2895983464 cites W1559052834 @default.
- W2895983464 cites W1578305628 @default.
- W2895983464 cites W183575708 @default.
- W2895983464 cites W1908016767 @default.
- W2895983464 cites W1964470356 @default.
- W2895983464 cites W1977948323 @default.
- W2895983464 cites W1989291440 @default.
- W2895983464 cites W2005609748 @default.
- W2895983464 cites W2008399778 @default.
- W2895983464 cites W2050145531 @default.
- W2895983464 cites W2082165536 @default.
- W2895983464 cites W2083931353 @default.
- W2895983464 cites W2099712288 @default.
- W2895983464 cites W2101938307 @default.
- W2895983464 cites W2104974755 @default.
- W2895983464 cites W2105372494 @default.
- W2895983464 cites W2105404016 @default.
- W2895983464 cites W2117248802 @default.
- W2895983464 cites W2126942199 @default.
- W2895983464 cites W2150066425 @default.
- W2895983464 cites W2151508759 @default.
- W2895983464 cites W2178272524 @default.
- W2895983464 cites W2214868166 @default.
- W2895983464 cites W2330339889 @default.
- W2895983464 cites W2440384215 @default.
- W2895983464 cites W2519683295 @default.
- W2895983464 cites W2559178909 @default.
- W2895983464 cites W2561219336 @default.
- W2895983464 cites W2566389903 @default.
- W2895983464 cites W2584471766 @default.
- W2895983464 cites W2604231069 @default.
- W2895983464 cites W2728277730 @default.
- W2895983464 cites W2738441955 @default.
- W2895983464 cites W2741885505 @default.
- W2895983464 cites W2756305021 @default.
- W2895983464 cites W2774796680 @default.
- W2895983464 cites W2963231581 @default.
- W2895983464 cites W3098068165 @default.
- W2895983464 cites W3100388886 @default.
- W2895983464 cites W55377555 @default.
- W2895983464 cites W63091017 @default.
- W2895983464 doi "https://doi.org/10.1007/978-3-030-01261-8_45" @default.
- W2895983464 hasPublicationYear "2018" @default.
- W2895983464 type Work @default.
- W2895983464 sameAs 2895983464 @default.
- W2895983464 citedByCount "36" @default.
- W2895983464 countsByYear W28959834642019 @default.
- W2895983464 countsByYear W28959834642020 @default.
- W2895983464 countsByYear W28959834642021 @default.
- W2895983464 countsByYear W28959834642022 @default.
- W2895983464 countsByYear W28959834642023 @default.
- W2895983464 crossrefType "book-chapter" @default.
- W2895983464 hasAuthorship W2895983464A5021908609 @default.
- W2895983464 hasAuthorship W2895983464A5071944294 @default.
- W2895983464 hasAuthorship W2895983464A5090341044 @default.
- W2895983464 hasConcept C105795698 @default.
- W2895983464 hasConcept C111919701 @default.
- W2895983464 hasConcept C11413529 @default.
- W2895983464 hasConcept C119599485 @default.
- W2895983464 hasConcept C127413603 @default.
- W2895983464 hasConcept C13280743 @default.
- W2895983464 hasConcept C134306372 @default.
- W2895983464 hasConcept C141353440 @default.
- W2895983464 hasConcept C142748172 @default.
- W2895983464 hasConcept C154945302 @default.
- W2895983464 hasConcept C160633673 @default.
- W2895983464 hasConcept C165064840 @default.
- W2895983464 hasConcept C177148314 @default.
- W2895983464 hasConcept C185798385 @default.
- W2895983464 hasConcept C205649164 @default.
- W2895983464 hasConcept C2779960059 @default.
- W2895983464 hasConcept C33923547 @default.
- W2895983464 hasConcept C41008148 @default.
- W2895983464 hasConcept C77618280 @default.
- W2895983464 hasConcept C78201319 @default.
- W2895983464 hasConceptScore W2895983464C105795698 @default.
- W2895983464 hasConceptScore W2895983464C111919701 @default.
- W2895983464 hasConceptScore W2895983464C11413529 @default.
- W2895983464 hasConceptScore W2895983464C119599485 @default.
- W2895983464 hasConceptScore W2895983464C127413603 @default.
- W2895983464 hasConceptScore W2895983464C13280743 @default.
- W2895983464 hasConceptScore W2895983464C134306372 @default.
- W2895983464 hasConceptScore W2895983464C141353440 @default.
- W2895983464 hasConceptScore W2895983464C142748172 @default.
- W2895983464 hasConceptScore W2895983464C154945302 @default.
- W2895983464 hasConceptScore W2895983464C160633673 @default.
- W2895983464 hasConceptScore W2895983464C165064840 @default.
- W2895983464 hasConceptScore W2895983464C177148314 @default.