Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048552438> ?p ?o ?g. }
- W3048552438 abstract "To what extent are two images picturing the same 3D surfaces? Even when this is a known scene, the answer typically requires an expensive search across scale space, with matching and geometric verification of large sets of local features. This expense is further multiplied when a query image is evaluated against a gallery, e.g. in visual relocalization. While we don't obviate the need for geometric verification, we propose an interpretable image-embedding that cuts the search in scale space to essentially a lookup. Our approach measures the asymmetric relation between two images. The model then learns a scene-specific measure of similarity, from training examples with known 3D visible-surface overlaps. The result is that we can quickly identify, for example, which test image is a close-up version of another, and by what scale factor. Subsequently, local features need only be detected at that scale. We validate our scene-specific model by showing how this embedding yields competitive image-matching results, while being simpler, faster, and also interpretable by humans." @default.
- W3048552438 created "2020-08-18" @default.
- W3048552438 creator A5016559942 @default.
- W3048552438 creator A5028617313 @default.
- W3048552438 creator A5034550765 @default.
- W3048552438 creator A5038405331 @default.
- W3048552438 creator A5077630267 @default.
- W3048552438 date "2020-08-13" @default.
- W3048552438 modified "2023-09-27" @default.
- W3048552438 title "Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings." @default.
- W3048552438 cites W153084048 @default.
- W3048552438 cites W1606766208 @default.
- W3048552438 cites W1691728462 @default.
- W3048552438 cites W1908016767 @default.
- W3048552438 cites W1909224301 @default.
- W3048552438 cites W1926837203 @default.
- W3048552438 cites W1953588267 @default.
- W3048552438 cites W1972378554 @default.
- W3048552438 cites W1989476314 @default.
- W3048552438 cites W1989484209 @default.
- W3048552438 cites W2029143333 @default.
- W3048552438 cites W2046166954 @default.
- W3048552438 cites W2057145757 @default.
- W3048552438 cites W2057388754 @default.
- W3048552438 cites W2071027807 @default.
- W3048552438 cites W2073761981 @default.
- W3048552438 cites W2099443716 @default.
- W3048552438 cites W2102481828 @default.
- W3048552438 cites W2103924867 @default.
- W3048552438 cites W2109863423 @default.
- W3048552438 cites W2118269922 @default.
- W3048552438 cites W2138621090 @default.
- W3048552438 cites W2141362318 @default.
- W3048552438 cites W2143432975 @default.
- W3048552438 cites W2144578488 @default.
- W3048552438 cites W2151103935 @default.
- W3048552438 cites W2156598602 @default.
- W3048552438 cites W2164488048 @default.
- W3048552438 cites W2179042386 @default.
- W3048552438 cites W2194775991 @default.
- W3048552438 cites W2200124539 @default.
- W3048552438 cites W2238402354 @default.
- W3048552438 cites W2337790388 @default.
- W3048552438 cites W2340690086 @default.
- W3048552438 cites W2439114332 @default.
- W3048552438 cites W2471962767 @default.
- W3048552438 cites W2522940611 @default.
- W3048552438 cites W2612112834 @default.
- W3048552438 cites W2728498859 @default.
- W3048552438 cites W2769651498 @default.
- W3048552438 cites W2892865870 @default.
- W3048552438 cites W2906685663 @default.
- W3048552438 cites W2922243907 @default.
- W3048552438 cites W2951870616 @default.
- W3048552438 cites W2953271441 @default.
- W3048552438 cites W2962796133 @default.
- W3048552438 cites W2962936818 @default.
- W3048552438 cites W2963157250 @default.
- W3048552438 cites W2963284197 @default.
- W3048552438 cites W2963346260 @default.
- W3048552438 cites W2963604457 @default.
- W3048552438 cites W2963690776 @default.
- W3048552438 cites W2963760790 @default.
- W3048552438 cites W2963856988 @default.
- W3048552438 cites W2963899908 @default.
- W3048552438 cites W2963928593 @default.
- W3048552438 cites W2964175348 @default.
- W3048552438 cites W2973665503 @default.
- W3048552438 cites W3034438849 @default.
- W3048552438 cites W3102327032 @default.
- W3048552438 cites W3102362806 @default.
- W3048552438 cites W782743827 @default.
- W3048552438 hasPublicationYear "2020" @default.
- W3048552438 type Work @default.
- W3048552438 sameAs 3048552438 @default.
- W3048552438 citedByCount "0" @default.
- W3048552438 crossrefType "posted-content" @default.
- W3048552438 hasAuthorship W3048552438A5016559942 @default.
- W3048552438 hasAuthorship W3048552438A5028617313 @default.
- W3048552438 hasAuthorship W3048552438A5034550765 @default.
- W3048552438 hasAuthorship W3048552438A5038405331 @default.
- W3048552438 hasAuthorship W3048552438A5077630267 @default.
- W3048552438 hasConcept C103278499 @default.
- W3048552438 hasConcept C105795698 @default.
- W3048552438 hasConcept C111919701 @default.
- W3048552438 hasConcept C115961682 @default.
- W3048552438 hasConcept C124101348 @default.
- W3048552438 hasConcept C153180895 @default.
- W3048552438 hasConcept C154945302 @default.
- W3048552438 hasConcept C162324750 @default.
- W3048552438 hasConcept C165064840 @default.
- W3048552438 hasConcept C176217482 @default.
- W3048552438 hasConcept C205649164 @default.
- W3048552438 hasConcept C21547014 @default.
- W3048552438 hasConcept C25343380 @default.
- W3048552438 hasConcept C2778572836 @default.
- W3048552438 hasConcept C2778755073 @default.
- W3048552438 hasConcept C31972630 @default.
- W3048552438 hasConcept C33923547 @default.
- W3048552438 hasConcept C41008148 @default.