Matches in SemOpenAlex for { <https://semopenalex.org/work/W2608587748> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2608587748 abstract "Initializing optical flow field by either sparse descriptor matching or dense patch matches has been proved to be particularly useful for capturing large displacements. In this paper, we present a pyramidal gradient matching approach that can provide dense matches for highly accurate and efficient optical flow estimation. A novel contribution of our method is that image gradient is used to describe image patches and proved to be able to produce robust matching. Therefore, our method is more efficient than methods that adopt special features (like SIFT) or patch distance metric. Moreover, we find that image gradient is scalable for optical flow estimation, which means we can use different levels of gradient feature (for example, full gradients or only direction information of gradients) to obtain different complexity without dramatic changes in accuracy. Another contribution is that we uncover the secrets of limited PatchMatch through a thorough analysis and design a pyramidal matching framework based these secrets. Our pyramidal matching framework is aimed at robust gradient matching and effective to grow inliers and reject outliers. In this framework, we present some special enhancements for outlier filtering in gradient matching. By initializing EpicFlow with our matches, experimental results show that our method is efficient and robust (ranking 1st on both clean pass and final pass of MPI Sintel dataset among published methods)." @default.
- W2608587748 created "2017-05-05" @default.
- W2608587748 creator A5048659848 @default.
- W2608587748 date "2017-04-11" @default.
- W2608587748 modified "2023-09-27" @default.
- W2608587748 title "Pyramidal Gradient Matching for Optical Flow Estimation." @default.
- W2608587748 cites W1563651445 @default.
- W2608587748 cites W1951289974 @default.
- W2608587748 cites W1993120651 @default.
- W2608587748 cites W2033104631 @default.
- W2608587748 cites W2147253850 @default.
- W2608587748 cites W2150066425 @default.
- W2608587748 cites W2165245371 @default.
- W2608587748 cites W2326743484 @default.
- W2608587748 cites W2495756989 @default.
- W2608587748 cites W303181297 @default.
- W2608587748 hasPublicationYear "2017" @default.
- W2608587748 type Work @default.
- W2608587748 sameAs 2608587748 @default.
- W2608587748 citedByCount "1" @default.
- W2608587748 countsByYear W26085877482017 @default.
- W2608587748 crossrefType "posted-content" @default.
- W2608587748 hasAuthorship W2608587748A5048659848 @default.
- W2608587748 hasConcept C105795698 @default.
- W2608587748 hasConcept C114466953 @default.
- W2608587748 hasConcept C115961682 @default.
- W2608587748 hasConcept C138885662 @default.
- W2608587748 hasConcept C153180895 @default.
- W2608587748 hasConcept C154945302 @default.
- W2608587748 hasConcept C155542232 @default.
- W2608587748 hasConcept C162324750 @default.
- W2608587748 hasConcept C165064840 @default.
- W2608587748 hasConcept C176217482 @default.
- W2608587748 hasConcept C199360897 @default.
- W2608587748 hasConcept C21547014 @default.
- W2608587748 hasConcept C2776401178 @default.
- W2608587748 hasConcept C33923547 @default.
- W2608587748 hasConcept C41008148 @default.
- W2608587748 hasConcept C41895202 @default.
- W2608587748 hasConcept C61265191 @default.
- W2608587748 hasConcept C79337645 @default.
- W2608587748 hasConceptScore W2608587748C105795698 @default.
- W2608587748 hasConceptScore W2608587748C114466953 @default.
- W2608587748 hasConceptScore W2608587748C115961682 @default.
- W2608587748 hasConceptScore W2608587748C138885662 @default.
- W2608587748 hasConceptScore W2608587748C153180895 @default.
- W2608587748 hasConceptScore W2608587748C154945302 @default.
- W2608587748 hasConceptScore W2608587748C155542232 @default.
- W2608587748 hasConceptScore W2608587748C162324750 @default.
- W2608587748 hasConceptScore W2608587748C165064840 @default.
- W2608587748 hasConceptScore W2608587748C176217482 @default.
- W2608587748 hasConceptScore W2608587748C199360897 @default.
- W2608587748 hasConceptScore W2608587748C21547014 @default.
- W2608587748 hasConceptScore W2608587748C2776401178 @default.
- W2608587748 hasConceptScore W2608587748C33923547 @default.
- W2608587748 hasConceptScore W2608587748C41008148 @default.
- W2608587748 hasConceptScore W2608587748C41895202 @default.
- W2608587748 hasConceptScore W2608587748C61265191 @default.
- W2608587748 hasConceptScore W2608587748C79337645 @default.
- W2608587748 hasLocation W26085877481 @default.
- W2608587748 hasOpenAccess W2608587748 @default.
- W2608587748 hasPrimaryLocation W26085877481 @default.
- W2608587748 hasRelatedWork W1987959715 @default.
- W2608587748 hasRelatedWork W2056215208 @default.
- W2608587748 hasRelatedWork W2061081385 @default.
- W2608587748 hasRelatedWork W2129520143 @default.
- W2608587748 hasRelatedWork W2211236345 @default.
- W2608587748 hasRelatedWork W2441099548 @default.
- W2608587748 hasRelatedWork W2472768686 @default.
- W2608587748 hasRelatedWork W2501937149 @default.
- W2608587748 hasRelatedWork W2638822030 @default.
- W2608587748 hasRelatedWork W2738028674 @default.
- W2608587748 hasRelatedWork W2762442437 @default.
- W2608587748 hasRelatedWork W2904032066 @default.
- W2608587748 hasRelatedWork W2912239483 @default.
- W2608587748 hasRelatedWork W2952606313 @default.
- W2608587748 hasRelatedWork W2953504521 @default.
- W2608587748 hasRelatedWork W2965340459 @default.
- W2608587748 hasRelatedWork W3004287368 @default.
- W2608587748 hasRelatedWork W3102169278 @default.
- W2608587748 hasRelatedWork W3116155102 @default.
- W2608587748 hasRelatedWork W3149304110 @default.
- W2608587748 isParatext "false" @default.
- W2608587748 isRetracted "false" @default.
- W2608587748 magId "2608587748" @default.
- W2608587748 workType "article" @default.