FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4360770819> ?p ?o ?g. }

• W4360770819 endingPage "2851" @default.
• W4360770819 startingPage "2844" @default.
• W4360770819 abstract "There are increasing interests of studying the video-to-depth (V2D) problem with machine learning techniques. While earlier methods directly learn a mapping from images to depth maps and camera poses, more recent works enforce multi-view geometry constraints through optimization embedded in the learning framework. This paper presents a novel optimization method based on recurrent neural networks to further exploit the potential of neural networks in V2D. Specifically, our neural optimizer alternately updates the depth and camera poses through iterations to minimize a feature-metric cost, and two gated recurrent units iteratively improve the results by tracing historical information. Extensive experimental results demonstrate that our method outperforms previous methods and is more efficient in computation and memory consumption than cost-volume-based methods. In particular, our self-supervised method outperforms previous supervised methods on the KITTI and ScanNet datasets. Our source code will be made public." @default.
• W4360770819 created "2023-03-25" @default.
• W4360770819 creator A5013549550 @default.
• W4360770819 creator A5019743637 @default.
• W4360770819 creator A5029170925 @default.
• W4360770819 creator A5052772478 @default.
• W4360770819 creator A5060851814 @default.
• W4360770819 creator A5069033376 @default.
• W4360770819 creator A5084953118 @default.
• W4360770819 date "2023-05-01" @default.
• W4360770819 modified "2023-10-01" @default.
• W4360770819 title "DRO: Deep Recurrent Optimizer for Video to Depth" @default.
• W4360770819 cites W2133665775 @default.
• W4360770819 cites W2194775991 @default.
• W4360770819 cites W2198618282 @default.
• W4360770819 cites W2474281075 @default.
• W4360770819 cites W2561074213 @default.
• W4360770819 cites W2593414960 @default.
• W4360770819 cites W2594519801 @default.
• W4360770819 cites W2609883120 @default.
• W4360770819 cites W2830339951 @default.
• W4360770819 cites W2887825894 @default.
• W4360770819 cites W2890949887 @default.
• W4360770819 cites W2949023359 @default.
• W4360770819 cites W2962793285 @default.
• W4360770819 cites W2962816904 @default.
• W4360770819 cites W2963216700 @default.
• W4360770819 cites W2963488291 @default.
• W4360770819 cites W2963583471 @default.
• W4360770819 cites W2963654727 @default.
• W4360770819 cites W2963906250 @default.
• W4360770819 cites W2964968086 @default.
• W4360770819 cites W2981732213 @default.
• W4360770819 cites W2985775862 @default.
• W4360770819 cites W2997687993 @default.
• W4360770819 cites W3034364596 @default.
• W4360770819 cites W3034524082 @default.
• W4360770819 cites W3034530552 @default.
• W4360770819 cites W3034604951 @default.
• W4360770819 cites W3101765447 @default.
• W4360770819 cites W3107156787 @default.
• W4360770819 cites W3109908659 @default.
• W4360770819 cites W3110153602 @default.
• W4360770819 cites W3175377832 @default.
• W4360770819 cites W4206184617 @default.
• W4360770819 cites W612478963 @default.
• W4360770819 doi "https://doi.org/10.1109/lra.2023.3260724" @default.
• W4360770819 hasPublicationYear "2023" @default.
• W4360770819 type Work @default.
• W4360770819 citedByCount "0" @default.
• W4360770819 crossrefType "journal-article" @default.
• W4360770819 hasAuthorship W4360770819A5013549550 @default.
• W4360770819 hasAuthorship W4360770819A5019743637 @default.
• W4360770819 hasAuthorship W4360770819A5029170925 @default.
• W4360770819 hasAuthorship W4360770819A5052772478 @default.
• W4360770819 hasAuthorship W4360770819A5060851814 @default.
• W4360770819 hasAuthorship W4360770819A5069033376 @default.
• W4360770819 hasAuthorship W4360770819A5084953118 @default.
• W4360770819 hasBestOaLocation W43607708192 @default.
• W4360770819 hasConcept C108583219 @default.
• W4360770819 hasConcept C111919701 @default.
• W4360770819 hasConcept C11413529 @default.
• W4360770819 hasConcept C119857082 @default.
• W4360770819 hasConcept C127413603 @default.
• W4360770819 hasConcept C138673069 @default.
• W4360770819 hasConcept C138885662 @default.
• W4360770819 hasConcept C147168706 @default.
• W4360770819 hasConcept C153180895 @default.
• W4360770819 hasConcept C154945302 @default.
• W4360770819 hasConcept C165696696 @default.
• W4360770819 hasConcept C176217482 @default.
• W4360770819 hasConcept C177264268 @default.
• W4360770819 hasConcept C199360897 @default.
• W4360770819 hasConcept C21547014 @default.
• W4360770819 hasConcept C2776401178 @default.
• W4360770819 hasConcept C2776760102 @default.
• W4360770819 hasConcept C38652104 @default.
• W4360770819 hasConcept C41008148 @default.
• W4360770819 hasConcept C41895202 @default.
• W4360770819 hasConcept C45374587 @default.
• W4360770819 hasConcept C50644808 @default.
• W4360770819 hasConceptScore W4360770819C108583219 @default.
• W4360770819 hasConceptScore W4360770819C111919701 @default.
• W4360770819 hasConceptScore W4360770819C11413529 @default.
• W4360770819 hasConceptScore W4360770819C119857082 @default.
• W4360770819 hasConceptScore W4360770819C127413603 @default.
• W4360770819 hasConceptScore W4360770819C138673069 @default.
• W4360770819 hasConceptScore W4360770819C138885662 @default.
• W4360770819 hasConceptScore W4360770819C147168706 @default.
• W4360770819 hasConceptScore W4360770819C153180895 @default.
• W4360770819 hasConceptScore W4360770819C154945302 @default.
• W4360770819 hasConceptScore W4360770819C165696696 @default.
• W4360770819 hasConceptScore W4360770819C176217482 @default.
• W4360770819 hasConceptScore W4360770819C177264268 @default.
• W4360770819 hasConceptScore W4360770819C199360897 @default.
• W4360770819 hasConceptScore W4360770819C21547014 @default.
• W4360770819 hasConceptScore W4360770819C2776401178 @default.
• W4360770819 hasConceptScore W4360770819C2776760102 @default.

• next