FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949915105> ?p ?o ?g. }

• W2949915105 abstract "Depth estimation from a single image represents a very exciting challenge in computer vision. While other image-based depth sensing techniques leverage on the geometry between different viewpoints (e.g., stereo or structure from motion), the lack of these cues within a single image renders ill-posed the monocular depth estimation task. For inference, state-of-the-art encoder-decoder architectures for monocular depth estimation rely on effective feature representations learned at training time. For unsupervised training of these models, geometry has been effectively exploited by suitable images warping losses computed from views acquired by a stereo rig or a moving camera. In this paper, we make a further step forward showing that learning semantic information from images enables to improve effectively monocular depth estimation as well. In particular, by leveraging on semantically labeled images together with unsupervised signals gained by geometry through an image warping loss, we propose a deep learning approach aimed at joint semantic segmentation and depth estimation. Our overall learning framework is semi-supervised, as we deploy groundtruth data only in the semantic domain. At training time, our network learns a common feature representation for both tasks and a novel cross-task loss function is proposed. The experimental findings show how, jointly tackling depth prediction and semantic segmentation, allows to improve depth estimation accuracy. In particular, on the KITTI dataset our network outperforms state-of-the-art methods for monocular depth estimation." @default.
• W2949915105 created "2019-06-27" @default.
• W2949915105 creator A5025618347 @default.
• W2949915105 creator A5025804456 @default.
• W2949915105 creator A5036563362 @default.
• W2949915105 creator A5054437049 @default.
• W2949915105 creator A5072569849 @default.
• W2949915105 date "2018-10-09" @default.
• W2949915105 modified "2023-09-27" @default.
• W2949915105 title "Geometry meets semantics for semi-supervised monocular depth estimation" @default.
• W2949915105 cites W1522301498 @default.
• W2949915105 cites W1899309388 @default.
• W2949915105 cites W1901129140 @default.
• W2949915105 cites W1903029394 @default.
• W2949915105 cites W1905829557 @default.
• W2949915105 cites W1992178727 @default.
• W2949915105 cites W2100588357 @default.
• W2949915105 cites W2115579991 @default.
• W2949915105 cites W2132947399 @default.
• W2949915105 cites W2133665775 @default.
• W2949915105 cites W2150066425 @default.
• W2949915105 cites W2194775991 @default.
• W2949915105 cites W2300779272 @default.
• W2949915105 cites W2340897893 @default.
• W2949915105 cites W2343077198 @default.
• W2949915105 cites W2412782625 @default.
• W2949915105 cites W2520707372 @default.
• W2949915105 cites W2545985378 @default.
• W2949915105 cites W2560023338 @default.
• W2949915105 cites W2592939477 @default.
• W2949915105 cites W2609883120 @default.
• W2949915105 cites W2750215633 @default.
• W2949915105 cites W2785512290 @default.
• W2949915105 cites W2798512429 @default.
• W2949915105 cites W2810398680 @default.
• W2949915105 cites W2876993306 @default.
• W2949915105 cites W2913483780 @default.
• W2949915105 cites W2950372243 @default.
• W2949915105 cites W2950477723 @default.
• W2949915105 cites W2951333975 @default.
• W2949915105 cites W2962835968 @default.
• W2949915105 cites W2962891704 @default.
• W2949915105 cites W2963583471 @default.
• W2949915105 cites W2963591054 @default.
• W2949915105 cites W2963654727 @default.
• W2949915105 cites W2963677766 @default.
• W2949915105 cites W2963881378 @default.
• W2949915105 cites W2964288706 @default.
• W2949915105 hasPublicationYear "2018" @default.
• W2949915105 type Work @default.
• W2949915105 sameAs 2949915105 @default.
• W2949915105 citedByCount "5" @default.
• W2949915105 countsByYear W29499151052019 @default.
• W2949915105 countsByYear W29499151052020 @default.
• W2949915105 countsByYear W29499151052021 @default.
• W2949915105 crossrefType "posted-content" @default.
• W2949915105 hasAuthorship W2949915105A5025618347 @default.
• W2949915105 hasAuthorship W2949915105A5025804456 @default.
• W2949915105 hasAuthorship W2949915105A5036563362 @default.
• W2949915105 hasAuthorship W2949915105A5054437049 @default.
• W2949915105 hasAuthorship W2949915105A5072569849 @default.
• W2949915105 hasConcept C108583219 @default.
• W2949915105 hasConcept C115961682 @default.
• W2949915105 hasConcept C138885662 @default.
• W2949915105 hasConcept C141268832 @default.
• W2949915105 hasConcept C153083717 @default.
• W2949915105 hasConcept C153180895 @default.
• W2949915105 hasConcept C154945302 @default.
• W2949915105 hasConcept C157202957 @default.
• W2949915105 hasConcept C169760540 @default.
• W2949915105 hasConcept C184337299 @default.
• W2949915105 hasConcept C199360897 @default.
• W2949915105 hasConcept C26760741 @default.
• W2949915105 hasConcept C2776214188 @default.
• W2949915105 hasConcept C2776401178 @default.
• W2949915105 hasConcept C31972630 @default.
• W2949915105 hasConcept C41008148 @default.
• W2949915105 hasConcept C41895202 @default.
• W2949915105 hasConcept C52672216 @default.
• W2949915105 hasConcept C59404180 @default.
• W2949915105 hasConcept C65909025 @default.
• W2949915105 hasConcept C86803240 @default.
• W2949915105 hasConcept C89600930 @default.
• W2949915105 hasConceptScore W2949915105C108583219 @default.
• W2949915105 hasConceptScore W2949915105C115961682 @default.
• W2949915105 hasConceptScore W2949915105C138885662 @default.
• W2949915105 hasConceptScore W2949915105C141268832 @default.
• W2949915105 hasConceptScore W2949915105C153083717 @default.
• W2949915105 hasConceptScore W2949915105C153180895 @default.
• W2949915105 hasConceptScore W2949915105C154945302 @default.
• W2949915105 hasConceptScore W2949915105C157202957 @default.
• W2949915105 hasConceptScore W2949915105C169760540 @default.
• W2949915105 hasConceptScore W2949915105C184337299 @default.
• W2949915105 hasConceptScore W2949915105C199360897 @default.
• W2949915105 hasConceptScore W2949915105C26760741 @default.
• W2949915105 hasConceptScore W2949915105C2776214188 @default.
• W2949915105 hasConceptScore W2949915105C2776401178 @default.
• W2949915105 hasConceptScore W2949915105C31972630 @default.
• W2949915105 hasConceptScore W2949915105C41008148 @default.
• W2949915105 hasConceptScore W2949915105C41895202 @default.

• next