FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092756309> ?p ?o ?g. }

• W3092756309 endingPage "106804" @default.
• W3092756309 startingPage "106804" @default.
• W3092756309 abstract "Monocular image depth prediction is an interesting challenge in three-dimensional (3D) perception, the purpose of which is to obtain the geometric features of 3D scenes from two-dimensional (2D) images. At present, the deep learning method for monocular depth prediction has yielded good results, but this approach treats it as a supervised deep regression problem. A significant weakness of current methods is the need to collect reams of depth measurement data in actual scenarios for training. In this paper, we design a novel convolutional neural network (CNN) with an encoding and decoding structure to estimate the depth map from monocular RGB images based on basic principles of binocular stereo vision, and use rectified stereo pairs to train our network from scratch in an unsupervised learning method without any depth data. We also explore a new upsampling strategy to improve the output resolution, and introduce a new dynamic optimization strategy to enhance the training speed and prediction accuracy. Extensive experiments on the publicly available KITTI and Cityscapes datasets demonstrate that our approach is more accurate than competing methods. The findings of the proposed methodology illustrate that our CNN model can be utilized as depth completion from LIDAR images." @default.
• W3092756309 created "2020-10-22" @default.
• W3092756309 creator A5027222674 @default.
• W3092756309 creator A5067609651 @default.
• W3092756309 creator A5076766013 @default.
• W3092756309 date "2020-12-01" @default.
• W3092756309 modified "2023-10-15" @default.
• W3092756309 title "Monocular image depth prediction without depth sensors: An unsupervised learning method" @default.
• W3092756309 cites W1545195129 @default.
• W3092756309 cites W1677182931 @default.
• W3092756309 cites W1776042733 @default.
• W3092756309 cites W1803059841 @default.
• W3092756309 cites W1901129140 @default.
• W3092756309 cites W1905829557 @default.
• W3092756309 cites W2083047701 @default.
• W3092756309 cites W2108598243 @default.
• W3092756309 cites W2120657032 @default.
• W3092756309 cites W2123043875 @default.
• W3092756309 cites W2124907686 @default.
• W3092756309 cites W2132947399 @default.
• W3092756309 cites W2133665775 @default.
• W3092756309 cites W2139137304 @default.
• W3092756309 cites W2150066425 @default.
• W3092756309 cites W2194775991 @default.
• W3092756309 cites W2297909103 @default.
• W3092756309 cites W2300779272 @default.
• W3092756309 cites W2336968928 @default.
• W3092756309 cites W2340897893 @default.
• W3092756309 cites W2436453945 @default.
• W3092756309 cites W2520707372 @default.
• W3092756309 cites W2593414960 @default.
• W3092756309 cites W2605938684 @default.
• W3092756309 cites W2609883120 @default.
• W3092756309 cites W2617063137 @default.
• W3092756309 cites W2752782242 @default.
• W3092756309 cites W2774550181 @default.
• W3092756309 cites W2775906317 @default.
• W3092756309 cites W2798727000 @default.
• W3092756309 cites W2912529902 @default.
• W3092756309 cites W2948647700 @default.
• W3092756309 cites W2955092942 @default.
• W3092756309 cites W2962718160 @default.
• W3092756309 cites W2962850830 @default.
• W3092756309 cites W2963110069 @default.
• W3092756309 cites W2963488291 @default.
• W3092756309 cites W2963583471 @default.
• W3092756309 cites W2963591054 @default.
• W3092756309 cites W2963652981 @default.
• W3092756309 cites W2963654727 @default.
• W3092756309 cites W2963760790 @default.
• W3092756309 cites W2963906250 @default.
• W3092756309 cites W2964014680 @default.
• W3092756309 cites W2970414448 @default.
• W3092756309 cites W2972554665 @default.
• W3092756309 doi "https://doi.org/10.1016/j.asoc.2020.106804" @default.
• W3092756309 hasPublicationYear "2020" @default.
• W3092756309 type Work @default.
• W3092756309 sameAs 3092756309 @default.
• W3092756309 citedByCount "6" @default.
• W3092756309 countsByYear W30927563092021 @default.
• W3092756309 countsByYear W30927563092022 @default.
• W3092756309 countsByYear W30927563092023 @default.
• W3092756309 crossrefType "journal-article" @default.
• W3092756309 hasAuthorship W3092756309A5027222674 @default.
• W3092756309 hasAuthorship W3092756309A5067609651 @default.
• W3092756309 hasAuthorship W3092756309A5076766013 @default.
• W3092756309 hasConcept C108583219 @default.
• W3092756309 hasConcept C110384440 @default.
• W3092756309 hasConcept C115961682 @default.
• W3092756309 hasConcept C13280743 @default.
• W3092756309 hasConcept C136389625 @default.
• W3092756309 hasConcept C141268832 @default.
• W3092756309 hasConcept C153180895 @default.
• W3092756309 hasConcept C154945302 @default.
• W3092756309 hasConcept C169760540 @default.
• W3092756309 hasConcept C185798385 @default.
• W3092756309 hasConcept C205649164 @default.
• W3092756309 hasConcept C26760741 @default.
• W3092756309 hasConcept C31972630 @default.
• W3092756309 hasConcept C41008148 @default.
• W3092756309 hasConcept C50644808 @default.
• W3092756309 hasConcept C52672216 @default.
• W3092756309 hasConcept C65909025 @default.
• W3092756309 hasConcept C81363708 @default.
• W3092756309 hasConcept C82990744 @default.
• W3092756309 hasConcept C86803240 @default.
• W3092756309 hasConceptScore W3092756309C108583219 @default.
• W3092756309 hasConceptScore W3092756309C110384440 @default.
• W3092756309 hasConceptScore W3092756309C115961682 @default.
• W3092756309 hasConceptScore W3092756309C13280743 @default.
• W3092756309 hasConceptScore W3092756309C136389625 @default.
• W3092756309 hasConceptScore W3092756309C141268832 @default.
• W3092756309 hasConceptScore W3092756309C153180895 @default.
• W3092756309 hasConceptScore W3092756309C154945302 @default.
• W3092756309 hasConceptScore W3092756309C169760540 @default.
• W3092756309 hasConceptScore W3092756309C185798385 @default.
• W3092756309 hasConceptScore W3092756309C205649164 @default.
• W3092756309 hasConceptScore W3092756309C26760741 @default.

• next