FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2976021265> ?p ?o ?g. }

• W2976021265 endingPage "2395" @default.
• W2976021265 startingPage "2380" @default.
• W2976021265 abstract "Recent deep monocular depth estimation approaches based on supervised regression have achieved remarkable performance. However, they require costly ground truth annotations during training. To cope with this issue, in this paper we present a novel unsupervised deep learning approach for predicting depth maps. We introduce a new network architecture, named Progressive Fusion Network (PFN), that is specifically designed for binocular stereo depth estimation. This network is based on a multi-scale refinement strategy that combines the information provided by both stereo views. In addition, we propose to stack twice this network in order to form a cycle. This cycle approach can be interpreted as a form of data-augmentation since, at training time, the network learns both from the training set images (in the forward half-cycle) but also from the synthesized images (in the backward half-cycle). The architecture is jointly trained with adversarial learning. Extensive experiments on the publicly available datasets KITTI, Cityscapes and ApolloScape demonstrate the effectiveness of the proposed model which is competitive with other unsupervised deep learning methods for depth prediction." @default.
• W2976021265 created "2019-10-03" @default.
• W2976021265 creator A5027171279 @default.
• W2976021265 creator A5047852717 @default.
• W2976021265 creator A5053479862 @default.
• W2976021265 creator A5065059558 @default.
• W2976021265 creator A5069109233 @default.
• W2976021265 creator A5087319775 @default.
• W2976021265 date "2020-10-01" @default.
• W2976021265 modified "2023-09-27" @default.
• W2976021265 title "Progressive Fusion for Unsupervised Binocular Depth Estimation Using Cycled Networks" @default.
• W2976021265 cites W1803059841 @default.
• W2976021265 cites W1915250530 @default.
• W2976021265 cites W1992178727 @default.
• W2976021265 cites W2115579991 @default.
• W2976021265 cites W2133665775 @default.
• W2976021265 cites W2136000821 @default.
• W2976021265 cites W2150066425 @default.
• W2976021265 cites W2340897893 @default.
• W2976021265 cites W2440384215 @default.
• W2976021265 cites W2520707372 @default.
• W2976021265 cites W2560491685 @default.
• W2976021265 cites W2593414223 @default.
• W2976021265 cites W2593414960 @default.
• W2976021265 cites W2609883120 @default.
• W2976021265 cites W2795912842 @default.
• W2976021265 cites W2798414551 @default.
• W2976021265 cites W2830339951 @default.
• W2976021265 cites W2962793481 @default.
• W2976021265 cites W2962816904 @default.
• W2976021265 cites W2962891704 @default.
• W2976021265 cites W2963073614 @default.
• W2976021265 cites W2963110069 @default.
• W2976021265 cites W2963231581 @default.
• W2976021265 cites W2963292632 @default.
• W2976021265 cites W2963517541 @default.
• W2976021265 cites W2963522749 @default.
• W2976021265 cites W2963591054 @default.
• W2976021265 cites W2963619659 @default.
• W2976021265 cites W2963652981 @default.
• W2976021265 cites W2963654727 @default.
• W2976021265 cites W2963845150 @default.
• W2976021265 cites W2963872790 @default.
• W2976021265 cites W2963891416 @default.
• W2976021265 cites W2963906250 @default.
• W2976021265 cites W2964002510 @default.
• W2976021265 cites W2964014680 @default.
• W2976021265 cites W2968529893 @default.
• W2976021265 cites W2985775862 @default.
• W2976021265 cites W3100388886 @default.
• W2976021265 cites W3101639073 @default.
• W2976021265 cites W764651262 @default.
• W2976021265 doi "https://doi.org/10.1109/tpami.2019.2942928" @default.
• W2976021265 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31545713" @default.
• W2976021265 hasPublicationYear "2020" @default.
• W2976021265 type Work @default.
• W2976021265 sameAs 2976021265 @default.
• W2976021265 citedByCount "17" @default.
• W2976021265 countsByYear W29760212652020 @default.
• W2976021265 countsByYear W29760212652021 @default.
• W2976021265 countsByYear W29760212652022 @default.
• W2976021265 countsByYear W29760212652023 @default.
• W2976021265 crossrefType "journal-article" @default.
• W2976021265 hasAuthorship W2976021265A5027171279 @default.
• W2976021265 hasAuthorship W2976021265A5047852717 @default.
• W2976021265 hasAuthorship W2976021265A5053479862 @default.
• W2976021265 hasAuthorship W2976021265A5065059558 @default.
• W2976021265 hasAuthorship W2976021265A5069109233 @default.
• W2976021265 hasAuthorship W2976021265A5087319775 @default.
• W2976021265 hasBestOaLocation W29760212653 @default.
• W2976021265 hasConcept C108583219 @default.
• W2976021265 hasConcept C119857082 @default.
• W2976021265 hasConcept C146849305 @default.
• W2976021265 hasConcept C153180895 @default.
• W2976021265 hasConcept C154945302 @default.
• W2976021265 hasConcept C177264268 @default.
• W2976021265 hasConcept C193415008 @default.
• W2976021265 hasConcept C199360897 @default.
• W2976021265 hasConcept C38652104 @default.
• W2976021265 hasConcept C41008148 @default.
• W2976021265 hasConcept C50644808 @default.
• W2976021265 hasConcept C65909025 @default.
• W2976021265 hasConcept C8038995 @default.
• W2976021265 hasConceptScore W2976021265C108583219 @default.
• W2976021265 hasConceptScore W2976021265C119857082 @default.
• W2976021265 hasConceptScore W2976021265C146849305 @default.
• W2976021265 hasConceptScore W2976021265C153180895 @default.
• W2976021265 hasConceptScore W2976021265C154945302 @default.
• W2976021265 hasConceptScore W2976021265C177264268 @default.
• W2976021265 hasConceptScore W2976021265C193415008 @default.
• W2976021265 hasConceptScore W2976021265C199360897 @default.
• W2976021265 hasConceptScore W2976021265C38652104 @default.
• W2976021265 hasConceptScore W2976021265C41008148 @default.
• W2976021265 hasConceptScore W2976021265C50644808 @default.
• W2976021265 hasConceptScore W2976021265C65909025 @default.
• W2976021265 hasConceptScore W2976021265C8038995 @default.
• W2976021265 hasIssue "10" @default.
• W2976021265 hasLocation W29760212651 @default.

• next