FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201987110> ?p ?o ?g. }

• W3201987110 abstract "Optical flow is inherently a 2D search problem, and thus the computational complexity grows quadratically with respect to the search window, making large displacements matching infeasible for high-resolution images. In this paper, we take inspiration from Transformers and propose a new method for high-resolution optical flow estimation with significantly less computation. Specifically, a 1D attention operation is first applied in the vertical direction of the target image, and then a simple 1D correlation in the horizontal direction of the attended image is able to achieve 2D correspondence modeling effect. The directions of attention and correlation can also be exchanged, resulting in two 3D cost volumes that are concatenated for optical flow estimation. The novel 1D formulation empowers our method to scale to very high-resolution input images while maintaining competitive performance. Extensive experiments on Sintel, KITTI and real-world 4K (2160 × 3840) resolution images demonstrated the effectiveness and superiority of our proposed method. Code and models are available at https://github.com/haofeixu/flow1d." @default.
• W3201987110 created "2021-10-11" @default.
• W3201987110 creator A5017901486 @default.
• W3201987110 creator A5073998375 @default.
• W3201987110 creator A5076804411 @default.
• W3201987110 creator A5087872323 @default.
• W3201987110 creator A5090954747 @default.
• W3201987110 date "2021-10-01" @default.
• W3201987110 modified "2023-10-09" @default.
• W3201987110 title "High-Resolution Optical Flow from 1D Attention and Correlation" @default.
• W3201987110 cites W1513100184 @default.
• W3201987110 cites W1578985305 @default.
• W3201987110 cites W1915301860 @default.
• W3201987110 cites W1921093919 @default.
• W3201987110 cites W1951289974 @default.
• W3201987110 cites W2002217635 @default.
• W3201987110 cites W2033959528 @default.
• W3201987110 cites W2104974755 @default.
• W3201987110 cites W2117248802 @default.
• W3201987110 cites W2131747574 @default.
• W3201987110 cites W2148534289 @default.
• W3201987110 cites W2150066425 @default.
• W3201987110 cites W2492517581 @default.
• W3201987110 cites W2560474170 @default.
• W3201987110 cites W2737529999 @default.
• W3201987110 cites W2751023760 @default.
• W3201987110 cites W2942368658 @default.
• W3201987110 cites W2952825894 @default.
• W3201987110 cites W2963093735 @default.
• W3201987110 cites W2963210183 @default.
• W3201987110 cites W2963305757 @default.
• W3201987110 cites W2963782415 @default.
• W3201987110 cites W2964110616 @default.
• W3201987110 cites W2964123261 @default.
• W3201987110 cites W2964156315 @default.
• W3201987110 cites W2964199361 @default.
• W3201987110 cites W2980116241 @default.
• W3201987110 cites W2981689412 @default.
• W3201987110 cites W3024841368 @default.
• W3201987110 cites W3034514115 @default.
• W3201987110 cites W3096609285 @default.
• W3201987110 cites W3100280854 @default.
• W3201987110 cites W3100388886 @default.
• W3201987110 cites W764651262 @default.
• W3201987110 doi "https://doi.org/10.1109/iccv48922.2021.01033" @default.
• W3201987110 hasPublicationYear "2021" @default.
• W3201987110 type Work @default.
• W3201987110 sameAs 3201987110 @default.
• W3201987110 citedByCount "21" @default.
• W3201987110 countsByYear W32019871102022 @default.
• W3201987110 countsByYear W32019871102023 @default.
• W3201987110 crossrefType "proceedings-article" @default.
• W3201987110 hasAuthorship W3201987110A5017901486 @default.
• W3201987110 hasAuthorship W3201987110A5073998375 @default.
• W3201987110 hasAuthorship W3201987110A5076804411 @default.
• W3201987110 hasAuthorship W3201987110A5087872323 @default.
• W3201987110 hasAuthorship W3201987110A5090954747 @default.
• W3201987110 hasBestOaLocation W32019871102 @default.
• W3201987110 hasConcept C105795698 @default.
• W3201987110 hasConcept C11413529 @default.
• W3201987110 hasConcept C115635565 @default.
• W3201987110 hasConcept C115961682 @default.
• W3201987110 hasConcept C117220453 @default.
• W3201987110 hasConcept C120665830 @default.
• W3201987110 hasConcept C121332964 @default.
• W3201987110 hasConcept C127313418 @default.
• W3201987110 hasConcept C138268822 @default.
• W3201987110 hasConcept C154945302 @default.
• W3201987110 hasConcept C155542232 @default.
• W3201987110 hasConcept C165064840 @default.
• W3201987110 hasConcept C177264268 @default.
• W3201987110 hasConcept C179799912 @default.
• W3201987110 hasConcept C195956108 @default.
• W3201987110 hasConcept C199360897 @default.
• W3201987110 hasConcept C205372480 @default.
• W3201987110 hasConcept C2524010 @default.
• W3201987110 hasConcept C2776760102 @default.
• W3201987110 hasConcept C3020199158 @default.
• W3201987110 hasConcept C31972630 @default.
• W3201987110 hasConcept C33923547 @default.
• W3201987110 hasConcept C38349280 @default.
• W3201987110 hasConcept C41008148 @default.
• W3201987110 hasConcept C45374587 @default.
• W3201987110 hasConcept C62649853 @default.
• W3201987110 hasConceptScore W3201987110C105795698 @default.
• W3201987110 hasConceptScore W3201987110C11413529 @default.
• W3201987110 hasConceptScore W3201987110C115635565 @default.
• W3201987110 hasConceptScore W3201987110C115961682 @default.
• W3201987110 hasConceptScore W3201987110C117220453 @default.
• W3201987110 hasConceptScore W3201987110C120665830 @default.
• W3201987110 hasConceptScore W3201987110C121332964 @default.
• W3201987110 hasConceptScore W3201987110C127313418 @default.
• W3201987110 hasConceptScore W3201987110C138268822 @default.
• W3201987110 hasConceptScore W3201987110C154945302 @default.
• W3201987110 hasConceptScore W3201987110C155542232 @default.
• W3201987110 hasConceptScore W3201987110C165064840 @default.
• W3201987110 hasConceptScore W3201987110C177264268 @default.
• W3201987110 hasConceptScore W3201987110C179799912 @default.
• W3201987110 hasConceptScore W3201987110C195956108 @default.
• W3201987110 hasConceptScore W3201987110C199360897 @default.

• next