Matches in SemOpenAlex for { <https://semopenalex.org/work/W2946784906> ?p ?o ?g. }
- W2946784906 abstract "Depth estimation from a single underwater image is one of the most challenging problems and is highly ill-posed. Due to the absence of large generalized underwater depth datasets and the difficulty in obtaining ground truth depth-maps, supervised learning techniques such as direct depth regression cannot be used. In this paper, we propose an unsupervised method for depth estimation from a single underwater image taken `in the wild' by using haze as a cue for depth. Our approach is based on indirect depth-map estimation where we learn the mapping functions between unpaired RGB-D terrestrial images and arbitrary underwater images to estimate the required depth-map. We propose a method which is based on the principles of cycle-consistent learning and uses dense-block based auto-encoders as generator networks. We evaluate and compare our method both quantitatively and qualitatively on various underwater images with diverse attenuation and scattering conditions and show that our method produces state-of-the-art results for unsupervised depth estimation from a single underwater image." @default.
- W2946784906 created "2019-05-29" @default.
- W2946784906 creator A5006862080 @default.
- W2946784906 creator A5028546508 @default.
- W2946784906 date "2019-05-25" @default.
- W2946784906 modified "2023-09-23" @default.
- W2946784906 title "Unsupervised Single Image Underwater Depth Estimation" @default.
- W2946784906 cites W1754127052 @default.
- W2946784906 cites W1901129140 @default.
- W2946784906 cites W2091420866 @default.
- W2946784906 cites W2099471712 @default.
- W2946784906 cites W2116713824 @default.
- W2946784906 cites W2128254161 @default.
- W2946784906 cites W2133665775 @default.
- W2946784906 cites W2171740948 @default.
- W2946784906 cites W2194775991 @default.
- W2946784906 cites W2207585345 @default.
- W2946784906 cites W2214944377 @default.
- W2946784906 cites W2293581118 @default.
- W2946784906 cites W2294668072 @default.
- W2946784906 cites W2473029285 @default.
- W2946784906 cites W2508509730 @default.
- W2946784906 cites W2520707372 @default.
- W2946784906 cites W2559597482 @default.
- W2946784906 cites W2561074213 @default.
- W2946784906 cites W2747017299 @default.
- W2946784906 cites W2789771527 @default.
- W2946784906 cites W2899190185 @default.
- W2946784906 cites W2951179855 @default.
- W2946784906 cites W2962793481 @default.
- W2946784906 cites W2963372104 @default.
- W2946784906 cites W2963446712 @default.
- W2946784906 cites W2963760790 @default.
- W2946784906 cites W2963825193 @default.
- W2946784906 cites W3100476583 @default.
- W2946784906 hasPublicationYear "2019" @default.
- W2946784906 type Work @default.
- W2946784906 sameAs 2946784906 @default.
- W2946784906 citedByCount "0" @default.
- W2946784906 crossrefType "posted-content" @default.
- W2946784906 hasAuthorship W2946784906A5006862080 @default.
- W2946784906 hasAuthorship W2946784906A5028546508 @default.
- W2946784906 hasConcept C111368507 @default.
- W2946784906 hasConcept C115961682 @default.
- W2946784906 hasConcept C120665830 @default.
- W2946784906 hasConcept C121332964 @default.
- W2946784906 hasConcept C127313418 @default.
- W2946784906 hasConcept C141268832 @default.
- W2946784906 hasConcept C146849305 @default.
- W2946784906 hasConcept C153180895 @default.
- W2946784906 hasConcept C154945302 @default.
- W2946784906 hasConcept C184652730 @default.
- W2946784906 hasConcept C2524010 @default.
- W2946784906 hasConcept C2777210771 @default.
- W2946784906 hasConcept C31972630 @default.
- W2946784906 hasConcept C33923547 @default.
- W2946784906 hasConcept C41008148 @default.
- W2946784906 hasConcept C98083399 @default.
- W2946784906 hasConceptScore W2946784906C111368507 @default.
- W2946784906 hasConceptScore W2946784906C115961682 @default.
- W2946784906 hasConceptScore W2946784906C120665830 @default.
- W2946784906 hasConceptScore W2946784906C121332964 @default.
- W2946784906 hasConceptScore W2946784906C127313418 @default.
- W2946784906 hasConceptScore W2946784906C141268832 @default.
- W2946784906 hasConceptScore W2946784906C146849305 @default.
- W2946784906 hasConceptScore W2946784906C153180895 @default.
- W2946784906 hasConceptScore W2946784906C154945302 @default.
- W2946784906 hasConceptScore W2946784906C184652730 @default.
- W2946784906 hasConceptScore W2946784906C2524010 @default.
- W2946784906 hasConceptScore W2946784906C2777210771 @default.
- W2946784906 hasConceptScore W2946784906C31972630 @default.
- W2946784906 hasConceptScore W2946784906C33923547 @default.
- W2946784906 hasConceptScore W2946784906C41008148 @default.
- W2946784906 hasConceptScore W2946784906C98083399 @default.
- W2946784906 hasLocation W29467849061 @default.
- W2946784906 hasOpenAccess W2946784906 @default.
- W2946784906 hasPrimaryLocation W29467849061 @default.
- W2946784906 hasRelatedWork W2890002736 @default.
- W2946784906 hasRelatedWork W2890109053 @default.
- W2946784906 hasRelatedWork W2907508336 @default.
- W2946784906 hasRelatedWork W2936412503 @default.
- W2946784906 hasRelatedWork W2951333975 @default.
- W2946784906 hasRelatedWork W2952077493 @default.
- W2946784906 hasRelatedWork W2962456457 @default.
- W2946784906 hasRelatedWork W2965673159 @default.
- W2946784906 hasRelatedWork W2970544662 @default.
- W2946784906 hasRelatedWork W3003798263 @default.
- W2946784906 hasRelatedWork W3005302484 @default.
- W2946784906 hasRelatedWork W3009733913 @default.
- W2946784906 hasRelatedWork W305753977 @default.
- W2946784906 hasRelatedWork W3080712214 @default.
- W2946784906 hasRelatedWork W3105650719 @default.
- W2946784906 hasRelatedWork W3112163773 @default.
- W2946784906 hasRelatedWork W3127104920 @default.
- W2946784906 hasRelatedWork W3173475516 @default.
- W2946784906 hasRelatedWork W3174175265 @default.
- W2946784906 hasRelatedWork W3208602589 @default.
- W2946784906 isParatext "false" @default.
- W2946784906 isRetracted "false" @default.
- W2946784906 magId "2946784906" @default.