Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197804629> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W3197804629 endingPage "9" @default.
- W3197804629 startingPage "B" @default.
- W3197804629 abstract "Scene understanding is a central problem in a field of computer vision. Depth estimation, in particular, is one of the important applications in scene understanding, robotics, and 3-D reconstruction. Estimating a dense depth map from a single image is receiving increased attention because a monocular camera is popular, small and suitable for a wide range of environments. In addition, both multi-task learning and multi-stream, which use unlabeled information, improve the monocular depth estimation efficiently. However, there are only a few networks optimized for both of them. Therefore, in this paper, we propose a monocular depth estimation task with a multi-task and multistream network architecture. Furthermore, the integrated network which we develop makes use of depth gradient information and can be applied to both supervised and unsupervised learning. In our experiments, we confirmed that our supervised learning architecture improves the accuracy of depth estimation by 0.13 m on average. Additionally, the experimental result on unsupervised learning found that it improved structure-from-motion performance." @default.
- W3197804629 created "2021-09-13" @default.
- W3197804629 creator A5022675410 @default.
- W3197804629 creator A5030888958 @default.
- W3197804629 date "2021-09-01" @default.
- W3197804629 modified "2023-09-27" @default.
- W3197804629 title "Monocular Depth Estimation using Integrated Model with Multi-task Learning and Multi-stream" @default.
- W3197804629 cites W1905829557 @default.
- W3197804629 cites W1915250530 @default.
- W3197804629 cites W1992178727 @default.
- W3197804629 cites W2593584281 @default.
- W3197804629 cites W2750215633 @default.
- W3197804629 cites W2798927139 @default.
- W3197804629 cites W2938544580 @default.
- W3197804629 cites W2951234442 @default.
- W3197804629 cites W2951261569 @default.
- W3197804629 cites W2962807621 @default.
- W3197804629 doi "https://doi.org/10.1527/tjsai.36-5_b-kc6" @default.
- W3197804629 hasPublicationYear "2021" @default.
- W3197804629 type Work @default.
- W3197804629 sameAs 3197804629 @default.
- W3197804629 citedByCount "0" @default.
- W3197804629 crossrefType "journal-article" @default.
- W3197804629 hasAuthorship W3197804629A5022675410 @default.
- W3197804629 hasAuthorship W3197804629A5030888958 @default.
- W3197804629 hasBestOaLocation W31978046291 @default.
- W3197804629 hasConcept C119857082 @default.
- W3197804629 hasConcept C153180895 @default.
- W3197804629 hasConcept C154945302 @default.
- W3197804629 hasConcept C162324750 @default.
- W3197804629 hasConcept C187736073 @default.
- W3197804629 hasConcept C2780451532 @default.
- W3197804629 hasConcept C28006648 @default.
- W3197804629 hasConcept C31972630 @default.
- W3197804629 hasConcept C41008148 @default.
- W3197804629 hasConcept C65909025 @default.
- W3197804629 hasConcept C96250715 @default.
- W3197804629 hasConceptScore W3197804629C119857082 @default.
- W3197804629 hasConceptScore W3197804629C153180895 @default.
- W3197804629 hasConceptScore W3197804629C154945302 @default.
- W3197804629 hasConceptScore W3197804629C162324750 @default.
- W3197804629 hasConceptScore W3197804629C187736073 @default.
- W3197804629 hasConceptScore W3197804629C2780451532 @default.
- W3197804629 hasConceptScore W3197804629C28006648 @default.
- W3197804629 hasConceptScore W3197804629C31972630 @default.
- W3197804629 hasConceptScore W3197804629C41008148 @default.
- W3197804629 hasConceptScore W3197804629C65909025 @default.
- W3197804629 hasConceptScore W3197804629C96250715 @default.
- W3197804629 hasIssue "5" @default.
- W3197804629 hasLocation W31978046291 @default.
- W3197804629 hasLocation W31978046292 @default.
- W3197804629 hasOpenAccess W3197804629 @default.
- W3197804629 hasPrimaryLocation W31978046291 @default.
- W3197804629 hasRelatedWork W12016155 @default.
- W3197804629 hasRelatedWork W13538861 @default.
- W3197804629 hasRelatedWork W14789944 @default.
- W3197804629 hasRelatedWork W1980845 @default.
- W3197804629 hasRelatedWork W354571 @default.
- W3197804629 hasRelatedWork W3569651 @default.
- W3197804629 hasRelatedWork W592020 @default.
- W3197804629 hasRelatedWork W7785909 @default.
- W3197804629 hasRelatedWork W8218506 @default.
- W3197804629 hasRelatedWork W9218159 @default.
- W3197804629 hasVolume "36" @default.
- W3197804629 isParatext "false" @default.
- W3197804629 isRetracted "false" @default.
- W3197804629 magId "3197804629" @default.
- W3197804629 workType "article" @default.