FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2905255369> ?p ?o ?g. }

• W2905255369 abstract "Robust and accurate visual localization is a fundamental capability for numerous applications, such as autonomous driving, mobile robotics, or augmented reality. It remains, however, a challenging task, particularly for large-scale environments and in presence of significant appearance changes. State-of-the-art methods not only struggle with such scenarios, but are often too resource intensive for certain real-time applications. In this paper we propose HF-Net, a hierarchical localization approach based on a monolithic CNN that simultaneously predicts local features and global descriptors for accurate 6-DoF localization. We exploit the coarse-to-fine localization paradigm: we first perform a global retrieval to obtain location hypotheses and only later match local features within those candidate places. This hierarchical approach incurs significant runtime savings and makes our system suitable for real-time operation. By leveraging learned descriptors, our method achieves remarkable localization robustness across large variations of appearance and sets a new state-of-the-art on two challenging benchmarks for large-scale localization." @default.
• W2905255369 created "2018-12-22" @default.
• W2905255369 creator A5045300921 @default.
• W2905255369 creator A5047661610 @default.
• W2905255369 creator A5063529163 @default.
• W2905255369 creator A5083003222 @default.
• W2905255369 date "2018-12-09" @default.
• W2905255369 modified "2023-09-23" @default.
• W2905255369 title "From Coarse to Fine: Robust Hierarchical Localization at Large Scale" @default.
• W2905255369 cites W1491719799 @default.
• W2905255369 cites W1544092585 @default.
• W2905255369 cites W1552672384 @default.
• W2905255369 cites W1606766208 @default.
• W2905255369 cites W1821462560 @default.
• W2905255369 cites W1909224301 @default.
• W2905255369 cites W1979931042 @default.
• W2905255369 cites W1998728242 @default.
• W2905255369 cites W2046166954 @default.
• W2905255369 cites W2073761981 @default.
• W2905255369 cites W2085261163 @default.
• W2905255369 cites W2108598243 @default.
• W2905255369 cites W2110405746 @default.
• W2905255369 cites W2111308925 @default.
• W2905255369 cites W2125795712 @default.
• W2905255369 cites W2127061207 @default.
• W2905255369 cites W2141584146 @default.
• W2905255369 cites W2148809531 @default.
• W2905255369 cites W2151290401 @default.
• W2905255369 cites W2155056756 @default.
• W2905255369 cites W2179042386 @default.
• W2905255369 cites W2250384498 @default.
• W2905255369 cites W2278591674 @default.
• W2905255369 cites W2284646714 @default.
• W2905255369 cites W2402144811 @default.
• W2905255369 cites W2471962767 @default.
• W2905255369 cites W2495591376 @default.
• W2905255369 cites W2519683295 @default.
• W2905255369 cites W2522940611 @default.
• W2905255369 cites W2558027072 @default.
• W2905255369 cites W2605111497 @default.
• W2905255369 cites W2618011341 @default.
• W2905255369 cites W2736941579 @default.
• W2905255369 cites W2737094507 @default.
• W2905255369 cites W2740418457 @default.
• W2905255369 cites W2780675120 @default.
• W2905255369 cites W2795645133 @default.
• W2905255369 cites W2799352588 @default.
• W2905255369 cites W2890538051 @default.
• W2905255369 cites W2897085414 @default.
• W2905255369 cites W2899117197 @default.
• W2905255369 cites W2922243907 @default.
• W2905255369 cites W2962697512 @default.
• W2905255369 cites W2962743139 @default.
• W2905255369 cites W2963125010 @default.
• W2905255369 cites W2963157250 @default.
• W2905255369 cites W2963163009 @default.
• W2905255369 cites W2963210849 @default.
• W2905255369 cites W2963284197 @default.
• W2905255369 cites W2963286292 @default.
• W2905255369 cites W2963479576 @default.
• W2905255369 cites W2963531306 @default.
• W2905255369 cites W2963537932 @default.
• W2905255369 cites W2963677766 @default.
• W2905255369 cites W2963748588 @default.
• W2905255369 cites W2964073646 @default.
• W2905255369 cites W2964157791 @default.
• W2905255369 cites W2971023449 @default.
• W2905255369 cites W3043075211 @default.
• W2905255369 cites W2435623039 @default.
• W2905255369 hasPublicationYear "2018" @default.
• W2905255369 type Work @default.
• W2905255369 sameAs 2905255369 @default.
• W2905255369 citedByCount "2" @default.
• W2905255369 countsByYear W29052553692018 @default.
• W2905255369 countsByYear W29052553692021 @default.
• W2905255369 crossrefType "posted-content" @default.
• W2905255369 hasAuthorship W2905255369A5045300921 @default.
• W2905255369 hasAuthorship W2905255369A5047661610 @default.
• W2905255369 hasAuthorship W2905255369A5063529163 @default.
• W2905255369 hasAuthorship W2905255369A5083003222 @default.
• W2905255369 hasConcept C104317684 @default.
• W2905255369 hasConcept C121332964 @default.
• W2905255369 hasConcept C127413603 @default.
• W2905255369 hasConcept C153180895 @default.
• W2905255369 hasConcept C153715457 @default.
• W2905255369 hasConcept C154945302 @default.
• W2905255369 hasConcept C165696696 @default.
• W2905255369 hasConcept C185592680 @default.
• W2905255369 hasConcept C201995342 @default.
• W2905255369 hasConcept C2778755073 @default.
• W2905255369 hasConcept C2780451532 @default.
• W2905255369 hasConcept C31972630 @default.
• W2905255369 hasConcept C34413123 @default.
• W2905255369 hasConcept C38652104 @default.
• W2905255369 hasConcept C41008148 @default.
• W2905255369 hasConcept C55493867 @default.
• W2905255369 hasConcept C62520636 @default.
• W2905255369 hasConcept C63479239 @default.
• W2905255369 hasConcept C90509273 @default.
• W2905255369 hasConceptScore W2905255369C104317684 @default.

• next