Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891690292> ?p ?o ?g. }
- W2891690292 endingPage "1" @default.
- W2891690292 startingPage "1" @default.
- W2891690292 abstract "Capturing ground truth data to benchmark super-resolution (SR) is challenging. Therefore, current quantitative studies are mainly evaluated on simulated data artificially sampled from ground truth images. We argue that such evaluations overestimate the actual performance of SR methods compared to their behavior on real images. Toward bridging this simulated-to-real gap, we introduce the Super-Resolution Erlangen (SupER) database, the first comprehensive laboratory SR database of all-real acquisitions with pixel-wise ground truth. It consists of more than 80k images of 14 scenes combining different facets: CMOS sensor noise, real sampling at four resolution levels, nine scene motion types, two photometric conditions, and lossy video coding at five levels. As such, the database exceeds existing benchmarks by an order of magnitude in quality and quantity. This paper also benchmarks 19 popular single-image and multi-frame algorithms on our data. The benchmark comprises a quantitative study by exploiting ground truth data and qualitative evaluations in a large-scale observer study. We also rigorously investigate agreements between both evaluations from a statistical perspective. One interesting result is that top-performing methods on simulated data may be surpassed by others on real data. Our insights can spur further algorithm development, and the publicy available dataset can foster future evaluations." @default.
- W2891690292 created "2018-09-27" @default.
- W2891690292 creator A5004766356 @default.
- W2891690292 creator A5020211325 @default.
- W2891690292 creator A5032939618 @default.
- W2891690292 creator A5049250339 @default.
- W2891690292 creator A5062850220 @default.
- W2891690292 creator A5071978262 @default.
- W2891690292 date "2019-01-01" @default.
- W2891690292 modified "2023-10-16" @default.
- W2891690292 title "Toward Bridging the Simulated-to-Real Gap: Benchmarking Super-Resolution on Real Data" @default.
- W2891690292 cites W1526920952 @default.
- W2891690292 cites W1604428010 @default.
- W2891690292 cites W1930824406 @default.
- W2891690292 cites W1950594372 @default.
- W2891690292 cites W1982471090 @default.
- W2891690292 cites W1986707602 @default.
- W2891690292 cites W1987931295 @default.
- W2891690292 cites W1990416059 @default.
- W2891690292 cites W1992303731 @default.
- W2891690292 cites W1996863403 @default.
- W2891690292 cites W2006262236 @default.
- W2891690292 cites W2006462689 @default.
- W2891690292 cites W2010981316 @default.
- W2891690292 cites W2015015901 @default.
- W2891690292 cites W2016482162 @default.
- W2891690292 cites W2054781681 @default.
- W2891690292 cites W2067042811 @default.
- W2891690292 cites W2073623229 @default.
- W2891690292 cites W2091588468 @default.
- W2891690292 cites W2096609483 @default.
- W2891690292 cites W2099470017 @default.
- W2891690292 cites W2101131403 @default.
- W2891690292 cites W2102166818 @default.
- W2891690292 cites W2110633874 @default.
- W2891690292 cites W2117117414 @default.
- W2891690292 cites W2119302101 @default.
- W2891690292 cites W2121058967 @default.
- W2891690292 cites W2128148283 @default.
- W2891690292 cites W2133665775 @default.
- W2891690292 cites W2138598313 @default.
- W2891690292 cites W2142884912 @default.
- W2891690292 cites W2146395539 @default.
- W2891690292 cites W2148040994 @default.
- W2891690292 cites W2149669120 @default.
- W2891690292 cites W2150066425 @default.
- W2891690292 cites W2161907179 @default.
- W2891690292 cites W2162115569 @default.
- W2891690292 cites W2163523041 @default.
- W2891690292 cites W2165939075 @default.
- W2891690292 cites W2200594420 @default.
- W2891690292 cites W2201938402 @default.
- W2891690292 cites W2210480155 @default.
- W2891690292 cites W2214802144 @default.
- W2891690292 cites W2242218935 @default.
- W2891690292 cites W2263468737 @default.
- W2891690292 cites W2288980073 @default.
- W2891690292 cites W2295844283 @default.
- W2891690292 cites W2320725294 @default.
- W2891690292 cites W2417716951 @default.
- W2891690292 cites W2465552163 @default.
- W2891690292 cites W2516563544 @default.
- W2891690292 cites W2517589955 @default.
- W2891690292 cites W2534320940 @default.
- W2891690292 cites W2551161082 @default.
- W2891690292 cites W2565312867 @default.
- W2891690292 cites W2577691344 @default.
- W2891690292 cites W2607041014 @default.
- W2891690292 cites W2739757502 @default.
- W2891690292 cites W2741137940 @default.
- W2891690292 cites W2768814045 @default.
- W2891690292 cites W2866634454 @default.
- W2891690292 cites W2962767526 @default.
- W2891690292 cites W2962785568 @default.
- W2891690292 cites W2963037581 @default.
- W2891690292 cites W2963372104 @default.
- W2891690292 cites W2963470893 @default.
- W2891690292 cites W2964277374 @default.
- W2891690292 cites W2964325192 @default.
- W2891690292 cites W3105643535 @default.
- W2891690292 cites W4378761606 @default.
- W2891690292 cites W7682646 @default.
- W2891690292 cites W935139217 @default.
- W2891690292 doi "https://doi.org/10.1109/tpami.2019.2917037" @default.
- W2891690292 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31095478" @default.
- W2891690292 hasPublicationYear "2019" @default.
- W2891690292 type Work @default.
- W2891690292 sameAs 2891690292 @default.
- W2891690292 citedByCount "33" @default.
- W2891690292 countsByYear W28916902922019 @default.
- W2891690292 countsByYear W28916902922020 @default.
- W2891690292 countsByYear W28916902922021 @default.
- W2891690292 countsByYear W28916902922022 @default.
- W2891690292 countsByYear W28916902922023 @default.
- W2891690292 crossrefType "journal-article" @default.
- W2891690292 hasAuthorship W2891690292A5004766356 @default.
- W2891690292 hasAuthorship W2891690292A5020211325 @default.
- W2891690292 hasAuthorship W2891690292A5032939618 @default.