Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312638962> ?p ?o ?g. }
- W4312638962 abstract "We present a visual localization system that learns to estimate camera poses in the real world with the help of synthetic data. Despite significant progress in recent years, most learning-based approaches to visual localization target at a single domain and require a dense database of geo-tagged images to function well. To mitigate the data scarcity issue and improve the scalability of the neural localization models, we introduce TOPO-DataGen, a versatile synthetic data generation tool that traverses smoothly between the real and virtual world, hinged on the geographic camera viewpoint. New large-scale sim-to-real benchmark datasets are proposed to showcase and evaluate the utility of the said synthetic data. Our experiments reveal that synthetic data generically enhances the neural network performance on real data. Furthermore, we introduce CrossLoc, a cross-modal visual representation learning approach to pose estimation that makes full use of the scene coordinate ground truth via self-supervision. Without any extra data, CrossLoc significantly outperforms the state-of-the-art methods and achieves substantially higher real-data sample efficiency. Our code and datasets are all available at crossloc. github. io." @default.
- W4312638962 created "2023-01-05" @default.
- W4312638962 creator A5003912575 @default.
- W4312638962 creator A5018899131 @default.
- W4312638962 creator A5055394334 @default.
- W4312638962 creator A5059301227 @default.
- W4312638962 creator A5076521578 @default.
- W4312638962 date "2022-06-01" @default.
- W4312638962 modified "2023-10-01" @default.
- W4312638962 title "CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data" @default.
- W4312638962 cites W1973166102 @default.
- W4312638962 cites W1989476314 @default.
- W4312638962 cites W1991544872 @default.
- W4312638962 cites W2046166954 @default.
- W4312638962 cites W2073761981 @default.
- W4312638962 cites W2097649661 @default.
- W4312638962 cites W2194775991 @default.
- W4312638962 cites W2200124539 @default.
- W4312638962 cites W2322104590 @default.
- W4312638962 cites W2474696196 @default.
- W4312638962 cites W2556455135 @default.
- W4312638962 cites W2584731199 @default.
- W4312638962 cites W2740418457 @default.
- W4312638962 cites W2795645133 @default.
- W4312638962 cites W2795889831 @default.
- W4312638962 cites W2798927139 @default.
- W4312638962 cites W2804375128 @default.
- W4312638962 cites W2922243907 @default.
- W4312638962 cites W2943046656 @default.
- W4312638962 cites W2948467257 @default.
- W4312638962 cites W2951019013 @default.
- W4312638962 cites W2962705366 @default.
- W4312638962 cites W2963024893 @default.
- W4312638962 cites W2963856988 @default.
- W4312638962 cites W2964185501 @default.
- W4312638962 cites W2967390145 @default.
- W4312638962 cites W2973689592 @default.
- W4312638962 cites W2982101479 @default.
- W4312638962 cites W2987672160 @default.
- W4312638962 cites W2997032998 @default.
- W4312638962 cites W3004273024 @default.
- W4312638962 cites W3010479006 @default.
- W4312638962 cites W3017008958 @default.
- W4312638962 cites W3034225195 @default.
- W4312638962 cites W3034421932 @default.
- W4312638962 cites W3035655707 @default.
- W4312638962 cites W3047161199 @default.
- W4312638962 cites W3106462076 @default.
- W4312638962 cites W3110012487 @default.
- W4312638962 cites W3141835154 @default.
- W4312638962 cites W3176602998 @default.
- W4312638962 cites W3201181723 @default.
- W4312638962 cites W3203887644 @default.
- W4312638962 cites W4242761880 @default.
- W4312638962 doi "https://doi.org/10.1109/cvpr52688.2022.01684" @default.
- W4312638962 hasPublicationYear "2022" @default.
- W4312638962 type Work @default.
- W4312638962 citedByCount "4" @default.
- W4312638962 countsByYear W43126389622022 @default.
- W4312638962 countsByYear W43126389622023 @default.
- W4312638962 crossrefType "proceedings-article" @default.
- W4312638962 hasAuthorship W4312638962A5003912575 @default.
- W4312638962 hasAuthorship W4312638962A5018899131 @default.
- W4312638962 hasAuthorship W4312638962A5055394334 @default.
- W4312638962 hasAuthorship W4312638962A5059301227 @default.
- W4312638962 hasAuthorship W4312638962A5076521578 @default.
- W4312638962 hasBestOaLocation W43126389622 @default.
- W4312638962 hasConcept C119857082 @default.
- W4312638962 hasConcept C124101348 @default.
- W4312638962 hasConcept C13280743 @default.
- W4312638962 hasConcept C146849305 @default.
- W4312638962 hasConcept C154945302 @default.
- W4312638962 hasConcept C160920958 @default.
- W4312638962 hasConcept C177264268 @default.
- W4312638962 hasConcept C17744445 @default.
- W4312638962 hasConcept C185798385 @default.
- W4312638962 hasConcept C199360897 @default.
- W4312638962 hasConcept C199539241 @default.
- W4312638962 hasConcept C205649164 @default.
- W4312638962 hasConcept C2776359362 @default.
- W4312638962 hasConcept C2776760102 @default.
- W4312638962 hasConcept C36464697 @default.
- W4312638962 hasConcept C41008148 @default.
- W4312638962 hasConcept C48044578 @default.
- W4312638962 hasConcept C77088390 @default.
- W4312638962 hasConcept C94625758 @default.
- W4312638962 hasConceptScore W4312638962C119857082 @default.
- W4312638962 hasConceptScore W4312638962C124101348 @default.
- W4312638962 hasConceptScore W4312638962C13280743 @default.
- W4312638962 hasConceptScore W4312638962C146849305 @default.
- W4312638962 hasConceptScore W4312638962C154945302 @default.
- W4312638962 hasConceptScore W4312638962C160920958 @default.
- W4312638962 hasConceptScore W4312638962C177264268 @default.
- W4312638962 hasConceptScore W4312638962C17744445 @default.
- W4312638962 hasConceptScore W4312638962C185798385 @default.
- W4312638962 hasConceptScore W4312638962C199360897 @default.
- W4312638962 hasConceptScore W4312638962C199539241 @default.
- W4312638962 hasConceptScore W4312638962C205649164 @default.
- W4312638962 hasConceptScore W4312638962C2776359362 @default.
- W4312638962 hasConceptScore W4312638962C2776760102 @default.