FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204873281> ?p ?o ?g. }

• W3204873281 abstract "Benchmark datasets that measure camera pose accuracy have driven progress in visual re-localisation research. To obtain poses for thousands of images, it is common to use a reference algorithm to generate pseudo ground truth. Popular choices include Structure-from-Motion (SfM) and Simultaneous-Localisation-and-Mapping (SLAM) using additional sensors like depth cameras if available. Re-localisation benchmarks thus measure how well each method replicates the results of the reference algorithm. This begs the question whether the choice of the reference algorithm favours a certain family of re-localisation methods. This paper analyzes two widely used re-localisation datasets and shows that evaluation outcomes indeed vary with the choice of the reference algorithm. We thus question common beliefs in the re-localisation literature, namely that learning-based scene coordinate regression outperforms classical feature-based methods, and that RGB-D-based methods outperform RGB-based methods. We argue that any claims on ranking re-localisation methods should take the type of the reference algorithm, and the similarity of the methods to the reference algorithm, into account." @default.
• W3204873281 created "2021-10-11" @default.
• W3204873281 creator A5011683384 @default.
• W3204873281 creator A5034290170 @default.
• W3204873281 creator A5050722856 @default.
• W3204873281 creator A5056030247 @default.
• W3204873281 date "2021-10-01" @default.
• W3204873281 modified "2023-09-30" @default.
• W3204873281 title "On the Limits of Pseudo Ground Truth in Visual Camera Re-localisation" @default.
• W3204873281 cites W1565312575 @default.
• W3204873281 cites W1893935112 @default.
• W3204873281 cites W1921093919 @default.
• W3204873281 cites W1987488988 @default.
• W3204873281 cites W1987648924 @default.
• W3204873281 cites W1989476314 @default.
• W3204873281 cites W2021851106 @default.
• W3204873281 cites W2046166954 @default.
• W3204873281 cites W2073761981 @default.
• W3204873281 cites W2081605477 @default.
• W3204873281 cites W2085078372 @default.
• W3204873281 cites W2085261163 @default.
• W3204873281 cites W2097649661 @default.
• W3204873281 cites W2099940712 @default.
• W3204873281 cites W2105303354 @default.
• W3204873281 cites W2108134361 @default.
• W3204873281 cites W2108598243 @default.
• W3204873281 cites W2115362620 @default.
• W3204873281 cites W2115579991 @default.
• W3204873281 cites W2119851068 @default.
• W3204873281 cites W2124313187 @default.
• W3204873281 cites W2129201358 @default.
• W3204873281 cites W2136567909 @default.
• W3204873281 cites W2147453378 @default.
• W3204873281 cites W2149705965 @default.
• W3204873281 cites W2151103935 @default.
• W3204873281 cites W2155056756 @default.
• W3204873281 cites W2156939321 @default.
• W3204873281 cites W2170647363 @default.
• W3204873281 cites W2200124539 @default.
• W3204873281 cites W2278591674 @default.
• W3204873281 cites W2340897893 @default.
• W3204873281 cites W2396274919 @default.
• W3204873281 cites W2471962767 @default.
• W3204873281 cites W2472269674 @default.
• W3204873281 cites W2522940611 @default.
• W3204873281 cites W2528398598 @default.
• W3204873281 cites W2556455135 @default.
• W3204873281 cites W2558625610 @default.
• W3204873281 cites W2584731199 @default.
• W3204873281 cites W2593174349 @default.
• W3204873281 cites W2605111497 @default.
• W3204873281 cites W2737094507 @default.
• W3204873281 cites W2738551266 @default.
• W3204873281 cites W2741885505 @default.
• W3204873281 cites W2745839262 @default.
• W3204873281 cites W2795645133 @default.
• W3204873281 cites W2922243907 @default.
• W3204873281 cites W2951730755 @default.
• W3204873281 cites W2962705366 @default.
• W3204873281 cites W2963210849 @default.
• W3204873281 cites W2963272646 @default.
• W3204873281 cites W2963523575 @default.
• W3204873281 cites W2963588253 @default.
• W3204873281 cites W2963856988 @default.
• W3204873281 cites W2967591132 @default.
• W3204873281 cites W2973689592 @default.
• W3204873281 cites W2979458572 @default.
• W3204873281 cites W2982101479 @default.
• W3204873281 cites W2983134350 @default.
• W3204873281 cites W2987672160 @default.
• W3204873281 cites W3009928773 @default.
• W3204873281 cites W3010479006 @default.
• W3204873281 cites W3017008958 @default.
• W3204873281 cites W3034275286 @default.
• W3204873281 cites W3043075211 @default.
• W3204873281 cites W3092233714 @default.
• W3204873281 cites W3108543662 @default.
• W3204873281 cites W3141835154 @default.
• W3204873281 cites W4247250903 @default.
• W3204873281 doi "https://doi.org/10.1109/iccv48922.2021.00616" @default.
• W3204873281 hasPublicationYear "2021" @default.
• W3204873281 type Work @default.
• W3204873281 sameAs 3204873281 @default.
• W3204873281 citedByCount "18" @default.
• W3204873281 countsByYear W32048732812021 @default.
• W3204873281 countsByYear W32048732812022 @default.
• W3204873281 countsByYear W32048732812023 @default.
• W3204873281 crossrefType "proceedings-article" @default.
• W3204873281 hasAuthorship W3204873281A5011683384 @default.
• W3204873281 hasAuthorship W3204873281A5034290170 @default.
• W3204873281 hasAuthorship W3204873281A5050722856 @default.
• W3204873281 hasAuthorship W3204873281A5056030247 @default.
• W3204873281 hasBestOaLocation W32048732812 @default.
• W3204873281 hasConcept C103278499 @default.
• W3204873281 hasConcept C104114177 @default.
• W3204873281 hasConcept C115961682 @default.
• W3204873281 hasConcept C124101348 @default.
• W3204873281 hasConcept C13280743 @default.
• W3204873281 hasConcept C138885662 @default.
• W3204873281 hasConcept C146159030 @default.

• next