Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035472788> ?p ?o ?g. }
- W3035472788 abstract "We tackle the problem of establishing dense pixel-wise correspondences between a pair of images. In this work, we introduce Dual-Resolution Correspondence Networks (DualRC-Net), to obtain pixel-wise correspondences in a coarse-to-fine manner. DualRC-Net extracts both coarse- and fine- resolution feature maps. The coarse maps are used to produce a full but coarse 4D correlation tensor, which is then refined by a learnable neighbourhood consensus module. The fine-resolution feature maps are used to obtain the final dense correspondences guided by the refined coarse 4D correlation tensor. The selected coarse-resolution matching scores allow the fine-resolution features to focus only on a limited number of possible matches with high confidence. In this way, DualRC-Net dramatically increases matching reliability and localisation accuracy, while avoiding to apply the expensive 4D convolution kernels on fine-resolution feature maps. We comprehensively evaluate our method on large-scale public benchmarks including HPatches, InLoc, and Aachen Day-Night. It achieves the state-of-the-art results on all of them." @default.
- W3035472788 created "2020-06-19" @default.
- W3035472788 creator A5033459720 @default.
- W3035472788 creator A5056485902 @default.
- W3035472788 creator A5067395390 @default.
- W3035472788 creator A5070710525 @default.
- W3035472788 date "2020-06-16" @default.
- W3035472788 modified "2023-09-27" @default.
- W3035472788 title "Dual-Resolution Correspondence Networks" @default.
- W3035472788 cites W1677409904 @default.
- W3035472788 cites W1686810756 @default.
- W3035472788 cites W2090518410 @default.
- W3035472788 cites W2096758544 @default.
- W3035472788 cites W2104520769 @default.
- W3035472788 cites W2106199912 @default.
- W3035472788 cites W2111073598 @default.
- W3035472788 cites W2141584146 @default.
- W3035472788 cites W2151103935 @default.
- W3035472788 cites W2170282673 @default.
- W3035472788 cites W2179042386 @default.
- W3035472788 cites W2194775991 @default.
- W3035472788 cites W2197122596 @default.
- W3035472788 cites W2410575852 @default.
- W3035472788 cites W2471962767 @default.
- W3035472788 cites W2519683295 @default.
- W3035472788 cites W2565639579 @default.
- W3035472788 cites W2584979312 @default.
- W3035472788 cites W2592936284 @default.
- W3035472788 cites W2728498859 @default.
- W3035472788 cites W2737094507 @default.
- W3035472788 cites W2740418457 @default.
- W3035472788 cites W2754925132 @default.
- W3035472788 cites W2777921528 @default.
- W3035472788 cites W2779304298 @default.
- W3035472788 cites W2892865870 @default.
- W3035472788 cites W2951870616 @default.
- W3035472788 cites W2963210849 @default.
- W3035472788 cites W2963325280 @default.
- W3035472788 cites W2963748588 @default.
- W3035472788 cites W2963760790 @default.
- W3035472788 cites W2963827464 @default.
- W3035472788 cites W2964073646 @default.
- W3035472788 cites W2964121744 @default.
- W3035472788 cites W2964157791 @default.
- W3035472788 cites W2964175348 @default.
- W3035472788 cites W2970971581 @default.
- W3035472788 cites W2973665503 @default.
- W3035472788 cites W2982121679 @default.
- W3035472788 cites W2983230029 @default.
- W3035472788 cites W2985822417 @default.
- W3035472788 cites W2990655570 @default.
- W3035472788 cites W3001017583 @default.
- W3035472788 cites W3023872192 @default.
- W3035472788 cites W3034275286 @default.
- W3035472788 cites W3034411221 @default.
- W3035472788 cites W3035559192 @default.
- W3035472788 cites W3035578028 @default.
- W3035472788 cites W3043075211 @default.
- W3035472788 cites W3092135995 @default.
- W3035472788 cites W3094761124 @default.
- W3035472788 hasPublicationYear "2020" @default.
- W3035472788 type Work @default.
- W3035472788 sameAs 3035472788 @default.
- W3035472788 citedByCount "2" @default.
- W3035472788 countsByYear W30354727882020 @default.
- W3035472788 countsByYear W30354727882021 @default.
- W3035472788 crossrefType "posted-content" @default.
- W3035472788 hasAuthorship W3035472788A5033459720 @default.
- W3035472788 hasAuthorship W3035472788A5056485902 @default.
- W3035472788 hasAuthorship W3035472788A5067395390 @default.
- W3035472788 hasAuthorship W3035472788A5070710525 @default.
- W3035472788 hasConcept C105795698 @default.
- W3035472788 hasConcept C11413529 @default.
- W3035472788 hasConcept C120665830 @default.
- W3035472788 hasConcept C121332964 @default.
- W3035472788 hasConcept C138268822 @default.
- W3035472788 hasConcept C138885662 @default.
- W3035472788 hasConcept C153180895 @default.
- W3035472788 hasConcept C154945302 @default.
- W3035472788 hasConcept C155281189 @default.
- W3035472788 hasConcept C160633673 @default.
- W3035472788 hasConcept C165064840 @default.
- W3035472788 hasConcept C192209626 @default.
- W3035472788 hasConcept C2524010 @default.
- W3035472788 hasConcept C2776401178 @default.
- W3035472788 hasConcept C33923547 @default.
- W3035472788 hasConcept C41008148 @default.
- W3035472788 hasConcept C41895202 @default.
- W3035472788 hasConcept C45347329 @default.
- W3035472788 hasConcept C50644808 @default.
- W3035472788 hasConceptScore W3035472788C105795698 @default.
- W3035472788 hasConceptScore W3035472788C11413529 @default.
- W3035472788 hasConceptScore W3035472788C120665830 @default.
- W3035472788 hasConceptScore W3035472788C121332964 @default.
- W3035472788 hasConceptScore W3035472788C138268822 @default.
- W3035472788 hasConceptScore W3035472788C138885662 @default.
- W3035472788 hasConceptScore W3035472788C153180895 @default.
- W3035472788 hasConceptScore W3035472788C154945302 @default.
- W3035472788 hasConceptScore W3035472788C155281189 @default.
- W3035472788 hasConceptScore W3035472788C160633673 @default.