Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312607856> ?p ?o ?g. }
- W4312607856 endingPage "605" @default.
- W4312607856 startingPage "591" @default.
- W4312607856 abstract "Current deep learning methods for optical flow estimation often use spatial feature pyramids to extract image features. To get the correlation between images, they directly compute the cost volume of the obtained image features. In this process, fine object details tend to be ignored. To solve this fundamental problem, an object-scale adaptive optical flow estimation network is proposed, in which multi-scale features are selectively extracted and exploited using our developed feature selectable block (FSB). As a result, we can obtain the multi-scale receptive fields of objects at different scales in the image. To consolidate all image features generated from all scales, a new cost volume generation scheme called multi-scale cost volume generation block (MCVGB) is further proposed to aggregate information from different scales. Extensive experiments conducted on the Sintel and KITTI2015 datasets show that our proposed method can capture fine details of different scale objects with high accuracy and thus deliver superior performance over a number of state-of-the-art methods." @default.
- W4312607856 created "2023-01-05" @default.
- W4312607856 creator A5004996650 @default.
- W4312607856 creator A5051065845 @default.
- W4312607856 creator A5059248438 @default.
- W4312607856 date "2022-01-01" @default.
- W4312607856 modified "2023-10-16" @default.
- W4312607856 title "Object-Scale Adaptive Optical Flow Estimation Network" @default.
- W4312607856 cites W1867429401 @default.
- W4312607856 cites W1951289974 @default.
- W4312607856 cites W2097117768 @default.
- W4312607856 cites W2104974755 @default.
- W4312607856 cites W2131747574 @default.
- W4312607856 cites W2148534289 @default.
- W4312607856 cites W2150066425 @default.
- W4312607856 cites W2155302366 @default.
- W4312607856 cites W2168874984 @default.
- W4312607856 cites W2194775991 @default.
- W4312607856 cites W2548527721 @default.
- W4312607856 cites W2560474170 @default.
- W4312607856 cites W2922509574 @default.
- W4312607856 cites W2952825894 @default.
- W4312607856 cites W2963782415 @default.
- W4312607856 cites W2964156315 @default.
- W4312607856 cites W2980116241 @default.
- W4312607856 cites W2981578854 @default.
- W4312607856 cites W2998004016 @default.
- W4312607856 cites W2998452266 @default.
- W4312607856 cites W3100280854 @default.
- W4312607856 cites W3100388886 @default.
- W4312607856 cites W3109908659 @default.
- W4312607856 cites W3120194628 @default.
- W4312607856 cites W3164221504 @default.
- W4312607856 cites W3174911623 @default.
- W4312607856 cites W3176593467 @default.
- W4312607856 cites W37877361 @default.
- W4312607856 cites W764651262 @default.
- W4312607856 doi "https://doi.org/10.1007/978-3-031-20868-3_44" @default.
- W4312607856 hasPublicationYear "2022" @default.
- W4312607856 type Work @default.
- W4312607856 citedByCount "0" @default.
- W4312607856 crossrefType "book-chapter" @default.
- W4312607856 hasAuthorship W4312607856A5004996650 @default.
- W4312607856 hasAuthorship W4312607856A5051065845 @default.
- W4312607856 hasAuthorship W4312607856A5059248438 @default.
- W4312607856 hasConcept C111919701 @default.
- W4312607856 hasConcept C115961682 @default.
- W4312607856 hasConcept C121332964 @default.
- W4312607856 hasConcept C138885662 @default.
- W4312607856 hasConcept C153180895 @default.
- W4312607856 hasConcept C154945302 @default.
- W4312607856 hasConcept C155542232 @default.
- W4312607856 hasConcept C20556612 @default.
- W4312607856 hasConcept C2524010 @default.
- W4312607856 hasConcept C2776401178 @default.
- W4312607856 hasConcept C2777210771 @default.
- W4312607856 hasConcept C2778755073 @default.
- W4312607856 hasConcept C2781238097 @default.
- W4312607856 hasConcept C31972630 @default.
- W4312607856 hasConcept C33923547 @default.
- W4312607856 hasConcept C41008148 @default.
- W4312607856 hasConcept C41895202 @default.
- W4312607856 hasConcept C62520636 @default.
- W4312607856 hasConcept C98045186 @default.
- W4312607856 hasConceptScore W4312607856C111919701 @default.
- W4312607856 hasConceptScore W4312607856C115961682 @default.
- W4312607856 hasConceptScore W4312607856C121332964 @default.
- W4312607856 hasConceptScore W4312607856C138885662 @default.
- W4312607856 hasConceptScore W4312607856C153180895 @default.
- W4312607856 hasConceptScore W4312607856C154945302 @default.
- W4312607856 hasConceptScore W4312607856C155542232 @default.
- W4312607856 hasConceptScore W4312607856C20556612 @default.
- W4312607856 hasConceptScore W4312607856C2524010 @default.
- W4312607856 hasConceptScore W4312607856C2776401178 @default.
- W4312607856 hasConceptScore W4312607856C2777210771 @default.
- W4312607856 hasConceptScore W4312607856C2778755073 @default.
- W4312607856 hasConceptScore W4312607856C2781238097 @default.
- W4312607856 hasConceptScore W4312607856C31972630 @default.
- W4312607856 hasConceptScore W4312607856C33923547 @default.
- W4312607856 hasConceptScore W4312607856C41008148 @default.
- W4312607856 hasConceptScore W4312607856C41895202 @default.
- W4312607856 hasConceptScore W4312607856C62520636 @default.
- W4312607856 hasConceptScore W4312607856C98045186 @default.
- W4312607856 hasLocation W43126078561 @default.
- W4312607856 hasOpenAccess W4312607856 @default.
- W4312607856 hasPrimaryLocation W43126078561 @default.
- W4312607856 hasRelatedWork W1926323357 @default.
- W4312607856 hasRelatedWork W1965104004 @default.
- W4312607856 hasRelatedWork W2079759540 @default.
- W4312607856 hasRelatedWork W2092957489 @default.
- W4312607856 hasRelatedWork W2116675934 @default.
- W4312607856 hasRelatedWork W2123374136 @default.
- W4312607856 hasRelatedWork W2128076597 @default.
- W4312607856 hasRelatedWork W2171116555 @default.
- W4312607856 hasRelatedWork W2534746541 @default.
- W4312607856 hasRelatedWork W4281553171 @default.
- W4312607856 isParatext "false" @default.
- W4312607856 isRetracted "false" @default.