Matches in SemOpenAlex for { <https://semopenalex.org/work/W3110743750> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3110743750 abstract "Spherical cameras and the latest image processing techniques open up new horizons. In particular, methods based on Convolutional Neural Networks (CNNs) now give excellent results for optical flow estimation on perspective images. However, these approaches are highly dependent on their architectures and training datasets. This paper proposes to benefit from years of improvement in perspective images optical flow estimation and to apply it to omnidirectional ones without training on new datasets. Our network, OmniFlowNet, is built on a CNN specialized in perspective images. Its convolution operation is adapted to be consistent with the equirectangular projection. Tested on spherical datasets created with Blender <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> and several equirectangular videos realized from real indoor and outdoor scenes, OmniFlowNet shows better performance than its original network without extra training." @default.
- W3110743750 created "2020-12-21" @default.
- W3110743750 creator A5038700866 @default.
- W3110743750 creator A5062431046 @default.
- W3110743750 creator A5069727899 @default.
- W3110743750 creator A5088809198 @default.
- W3110743750 date "2021-01-10" @default.
- W3110743750 modified "2023-10-16" @default.
- W3110743750 title "OmniFlowNet: a Perspective Neural Network Adaptation for Optical Flow Estimation in Omnidirectional Images" @default.
- W3110743750 cites W1578285471 @default.
- W3110743750 cites W1921093919 @default.
- W3110743750 cites W1975129657 @default.
- W3110743750 cites W2034869517 @default.
- W3110743750 cites W2155893237 @default.
- W3110743750 cites W2166904397 @default.
- W3110743750 cites W2202251471 @default.
- W3110743750 cites W2560474170 @default.
- W3110743750 cites W2895250390 @default.
- W3110743750 cites W2895696451 @default.
- W3110743750 cites W2963318716 @default.
- W3110743750 cites W2964156315 @default.
- W3110743750 cites W2979485822 @default.
- W3110743750 cites W2999254410 @default.
- W3110743750 cites W3007471652 @default.
- W3110743750 cites W3100388886 @default.
- W3110743750 cites W3105244967 @default.
- W3110743750 cites W764651262 @default.
- W3110743750 doi "https://doi.org/10.1109/icpr48806.2021.9412745" @default.
- W3110743750 hasPublicationYear "2021" @default.
- W3110743750 type Work @default.
- W3110743750 sameAs 3110743750 @default.
- W3110743750 citedByCount "7" @default.
- W3110743750 countsByYear W31107437502022 @default.
- W3110743750 countsByYear W31107437502023 @default.
- W3110743750 crossrefType "proceedings-article" @default.
- W3110743750 hasAuthorship W3110743750A5038700866 @default.
- W3110743750 hasAuthorship W3110743750A5062431046 @default.
- W3110743750 hasAuthorship W3110743750A5069727899 @default.
- W3110743750 hasAuthorship W3110743750A5088809198 @default.
- W3110743750 hasBestOaLocation W31107437502 @default.
- W3110743750 hasConcept C11413529 @default.
- W3110743750 hasConcept C115961682 @default.
- W3110743750 hasConcept C120665830 @default.
- W3110743750 hasConcept C121332964 @default.
- W3110743750 hasConcept C12713177 @default.
- W3110743750 hasConcept C139807058 @default.
- W3110743750 hasConcept C153180895 @default.
- W3110743750 hasConcept C154945302 @default.
- W3110743750 hasConcept C155542232 @default.
- W3110743750 hasConcept C21822782 @default.
- W3110743750 hasConcept C24027999 @default.
- W3110743750 hasConcept C31972630 @default.
- W3110743750 hasConcept C41008148 @default.
- W3110743750 hasConcept C45347329 @default.
- W3110743750 hasConcept C50644808 @default.
- W3110743750 hasConcept C57493831 @default.
- W3110743750 hasConcept C76155785 @default.
- W3110743750 hasConcept C81363708 @default.
- W3110743750 hasConceptScore W3110743750C11413529 @default.
- W3110743750 hasConceptScore W3110743750C115961682 @default.
- W3110743750 hasConceptScore W3110743750C120665830 @default.
- W3110743750 hasConceptScore W3110743750C121332964 @default.
- W3110743750 hasConceptScore W3110743750C12713177 @default.
- W3110743750 hasConceptScore W3110743750C139807058 @default.
- W3110743750 hasConceptScore W3110743750C153180895 @default.
- W3110743750 hasConceptScore W3110743750C154945302 @default.
- W3110743750 hasConceptScore W3110743750C155542232 @default.
- W3110743750 hasConceptScore W3110743750C21822782 @default.
- W3110743750 hasConceptScore W3110743750C24027999 @default.
- W3110743750 hasConceptScore W3110743750C31972630 @default.
- W3110743750 hasConceptScore W3110743750C41008148 @default.
- W3110743750 hasConceptScore W3110743750C45347329 @default.
- W3110743750 hasConceptScore W3110743750C50644808 @default.
- W3110743750 hasConceptScore W3110743750C57493831 @default.
- W3110743750 hasConceptScore W3110743750C76155785 @default.
- W3110743750 hasConceptScore W3110743750C81363708 @default.
- W3110743750 hasLocation W31107437501 @default.
- W3110743750 hasLocation W31107437502 @default.
- W3110743750 hasLocation W31107437503 @default.
- W3110743750 hasLocation W31107437504 @default.
- W3110743750 hasLocation W31107437505 @default.
- W3110743750 hasOpenAccess W3110743750 @default.
- W3110743750 hasPrimaryLocation W31107437501 @default.
- W3110743750 hasRelatedWork W1972819412 @default.
- W3110743750 hasRelatedWork W2126905924 @default.
- W3110743750 hasRelatedWork W2281465300 @default.
- W3110743750 hasRelatedWork W2762689969 @default.
- W3110743750 hasRelatedWork W2964954556 @default.
- W3110743750 hasRelatedWork W3019910406 @default.
- W3110743750 hasRelatedWork W3205202509 @default.
- W3110743750 hasRelatedWork W4214562868 @default.
- W3110743750 hasRelatedWork W4293226380 @default.
- W3110743750 hasRelatedWork W4379536980 @default.
- W3110743750 isParatext "false" @default.
- W3110743750 isRetracted "false" @default.
- W3110743750 magId "3110743750" @default.
- W3110743750 workType "article" @default.