Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896920009> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2896920009 abstract "Monocular simultaneous localization and mapping (SLAM) is a key enabling technique for many computer vision and robotics applications. However, existing methods either can obtain only sparse or semi-dense maps in highly-textured image areas or fail to achieve a satisfactory reconstruction accuracy. In this paper, we present a new method based on a generative adversarial network,named DM-GAN, for real-time dense mapping based on a monocular camera. Specifcally, our depth generator network takes a semidense map obtained from motion stereo matching as a guidance to supervise dense depth prediction of a single RGB image. The depth generator is trained based on a combination of two loss functions, i.e. an adversarial loss for enforcing the generated depth maps to reside on the manifold of the true depth maps and a pixel-wise mean square error (MSE) for ensuring the correct absolute depth values. Extensive experiments on three public datasets demonstrate that our DM-GAN signifcantly outperforms the state-of-the-art methods in terms of greater reconstruction accuracy and higher depth completeness." @default.
- W2896920009 created "2018-10-26" @default.
- W2896920009 creator A5018974857 @default.
- W2896920009 creator A5032279676 @default.
- W2896920009 creator A5054649167 @default.
- W2896920009 creator A5064019693 @default.
- W2896920009 creator A5077687075 @default.
- W2896920009 creator A5082599988 @default.
- W2896920009 creator A5088751649 @default.
- W2896920009 date "2018-10-15" @default.
- W2896920009 modified "2023-09-30" @default.
- W2896920009 title "Monocular Camera Based Real-Time Dense Mapping Using Generative Adversarial Network" @default.
- W2896920009 cites W125693051 @default.
- W2896920009 cites W1595654559 @default.
- W2896920009 cites W1905829557 @default.
- W2896920009 cites W1970504153 @default.
- W2896920009 cites W2083047701 @default.
- W2896920009 cites W2083347703 @default.
- W2896920009 cites W2097117768 @default.
- W2896920009 cites W2119493293 @default.
- W2896920009 cites W2125416623 @default.
- W2896920009 cites W2151290401 @default.
- W2896920009 cites W2210972093 @default.
- W2896920009 cites W2300779272 @default.
- W2896920009 cites W2413819886 @default.
- W2896920009 cites W2566881119 @default.
- W2896920009 cites W2724339714 @default.
- W2896920009 cites W2766814309 @default.
- W2896920009 cites W3103648783 @default.
- W2896920009 cites W4211015534 @default.
- W2896920009 cites W612478963 @default.
- W2896920009 cites W801273237 @default.
- W2896920009 doi "https://doi.org/10.1145/3240508.3240564" @default.
- W2896920009 hasPublicationYear "2018" @default.
- W2896920009 type Work @default.
- W2896920009 sameAs 2896920009 @default.
- W2896920009 citedByCount "8" @default.
- W2896920009 countsByYear W28969200092018 @default.
- W2896920009 countsByYear W28969200092019 @default.
- W2896920009 countsByYear W28969200092020 @default.
- W2896920009 countsByYear W28969200092021 @default.
- W2896920009 crossrefType "proceedings-article" @default.
- W2896920009 hasAuthorship W2896920009A5018974857 @default.
- W2896920009 hasAuthorship W2896920009A5032279676 @default.
- W2896920009 hasAuthorship W2896920009A5054649167 @default.
- W2896920009 hasAuthorship W2896920009A5064019693 @default.
- W2896920009 hasAuthorship W2896920009A5077687075 @default.
- W2896920009 hasAuthorship W2896920009A5082599988 @default.
- W2896920009 hasAuthorship W2896920009A5088751649 @default.
- W2896920009 hasConcept C108583219 @default.
- W2896920009 hasConcept C154945302 @default.
- W2896920009 hasConcept C2988773926 @default.
- W2896920009 hasConcept C31972630 @default.
- W2896920009 hasConcept C37736160 @default.
- W2896920009 hasConcept C39890363 @default.
- W2896920009 hasConcept C41008148 @default.
- W2896920009 hasConcept C65909025 @default.
- W2896920009 hasConceptScore W2896920009C108583219 @default.
- W2896920009 hasConceptScore W2896920009C154945302 @default.
- W2896920009 hasConceptScore W2896920009C2988773926 @default.
- W2896920009 hasConceptScore W2896920009C31972630 @default.
- W2896920009 hasConceptScore W2896920009C37736160 @default.
- W2896920009 hasConceptScore W2896920009C39890363 @default.
- W2896920009 hasConceptScore W2896920009C41008148 @default.
- W2896920009 hasConceptScore W2896920009C65909025 @default.
- W2896920009 hasLocation W28969200091 @default.
- W2896920009 hasOpenAccess W2896920009 @default.
- W2896920009 hasPrimaryLocation W28969200091 @default.
- W2896920009 hasRelatedWork W2898421198 @default.
- W2896920009 hasRelatedWork W2901368259 @default.
- W2896920009 hasRelatedWork W2998996837 @default.
- W2896920009 hasRelatedWork W3020202994 @default.
- W2896920009 hasRelatedWork W3024390022 @default.
- W2896920009 hasRelatedWork W3156291593 @default.
- W2896920009 hasRelatedWork W3164279787 @default.
- W2896920009 hasRelatedWork W4296176982 @default.
- W2896920009 hasRelatedWork W4311460979 @default.
- W2896920009 hasRelatedWork W4313479464 @default.
- W2896920009 isParatext "false" @default.
- W2896920009 isRetracted "false" @default.
- W2896920009 magId "2896920009" @default.
- W2896920009 workType "article" @default.