Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092879848> ?p ?o ?g. }
Showing items 1 to 56 of
56
with 100 items per page.
- W3092879848 abstract "The crux of homography estimation is that the homography is characterized by the geometric correspondences between two related images rather than appearance features, which differs from typical image recognition tasks. Existing methods either decompose the task of homography estimation into several individual sub-problems and optimize them sequentially, or attempt to tackle it in an end-to-end manner by delegating the whole task to deep convolutional networks (CNNs). However, it is quite arduous for CNNs to learn the mapping function from appearance features of related images to the homography directly. In this paper, we propose to parse the geometric correspondences between related images explicitly to bridge the gap between deep appearance features and the homography. Furthermore, we propose a coarse-to-fine estimation framework to capture different scale of homography transformations and thus predict the homography in a stepwise-refining manner. Additionally, we propose a pyramidal supervision scheme to leverage an important prior concerning the homography estimation. Extensive experiments on two large-scale datasets demonstrate that our model advances the state-of-the-art performance significantly." @default.
- W3092879848 created "2020-10-22" @default.
- W3092879848 creator A5064842058 @default.
- W3092879848 creator A5069054353 @default.
- W3092879848 creator A5078487642 @default.
- W3092879848 date "2020-10-12" @default.
- W3092879848 modified "2023-09-27" @default.
- W3092879848 title "SRHEN" @default.
- W3092879848 cites W1505641881 @default.
- W3092879848 cites W1677409904 @default.
- W3092879848 cites W1977766639 @default.
- W3092879848 cites W2046434485 @default.
- W3092879848 cites W2057749491 @default.
- W3092879848 cites W2085261163 @default.
- W3092879848 cites W2117228865 @default.
- W3092879848 cites W2151103935 @default.
- W3092879848 cites W2168104347 @default.
- W3092879848 cites W2177274842 @default.
- W3092879848 cites W2556455135 @default.
- W3092879848 cites W2737260104 @default.
- W3092879848 cites W2884088147 @default.
- W3092879848 cites W2887833108 @default.
- W3092879848 cites W2905913346 @default.
- W3092879848 cites W3102327032 @default.
- W3092879848 cites W3103648783 @default.
- W3092879848 cites W4249418251 @default.
- W3092879848 doi "https://doi.org/10.1145/3394171.3413870" @default.
- W3092879848 hasPublicationYear "2020" @default.
- W3092879848 type Work @default.
- W3092879848 sameAs 3092879848 @default.
- W3092879848 citedByCount "2" @default.
- W3092879848 countsByYear W30928798482021 @default.
- W3092879848 countsByYear W30928798482023 @default.
- W3092879848 crossrefType "proceedings-article" @default.
- W3092879848 hasAuthorship W3092879848A5064842058 @default.
- W3092879848 hasAuthorship W3092879848A5069054353 @default.
- W3092879848 hasAuthorship W3092879848A5078487642 @default.
- W3092879848 hasConcept C41008148 @default.
- W3092879848 hasConceptScore W3092879848C41008148 @default.
- W3092879848 hasLocation W30928798481 @default.
- W3092879848 hasOpenAccess W3092879848 @default.
- W3092879848 hasPrimaryLocation W30928798481 @default.
- W3092879848 hasRelatedWork W2093578348 @default.
- W3092879848 hasRelatedWork W2130043461 @default.
- W3092879848 hasRelatedWork W2350741829 @default.
- W3092879848 hasRelatedWork W2358668433 @default.
- W3092879848 hasRelatedWork W2376932109 @default.
- W3092879848 hasRelatedWork W2382290278 @default.
- W3092879848 hasRelatedWork W2390279801 @default.
- W3092879848 hasRelatedWork W2748952813 @default.
- W3092879848 hasRelatedWork W2899084033 @default.
- W3092879848 hasRelatedWork W3004735627 @default.
- W3092879848 isParatext "false" @default.
- W3092879848 isRetracted "false" @default.
- W3092879848 magId "3092879848" @default.
- W3092879848 workType "article" @default.