Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100847195> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3100847195 endingPage "4437" @default.
- W3100847195 startingPage "4431" @default.
- W3100847195 abstract "Recently end-to-end unsupervised deep learning methods have demonstrated an impressive performance for visual depth and ego-motion estimation tasks. These data-based learning methods do not rely on the same limiting assumptions that geometry-based methods do. The encoder-decoder network has been widely used in the depth estimation and the RCNN has brought significant improvements in the ego-motion estimation. Furthermore, the latest use of generative adversarial nets (GANs) in depth and ego-motion estimation has demonstrated that the estimation could be further improved by generating pictures in the game learning process. This paper proposes a novel unsupervised network system for visual depth and ego-motion estimation- stacked generative adversarial network. It consists of a stack of GAN layers, of which the lowest layer estimates the depth and egomotion while the higher layers estimate the spatial features. It can also capture the temporal dynamic due to the use of a recurrent representation across the layers. We select the most commonly used KITTI data set for evaluation. The evaluation results show that our proposed method can produce better or comparable results in depth and ego-motion estimation." @default.
- W3100847195 created "2020-11-23" @default.
- W3100847195 creator A5046559236 @default.
- W3100847195 creator A5076389260 @default.
- W3100847195 date "2019-10-01" @default.
- W3100847195 modified "2023-10-05" @default.
- W3100847195 title "SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation With Stacked Generative Adversarial Networks" @default.
- W3100847195 cites W1600744878 @default.
- W3100847195 cites W2150066425 @default.
- W3100847195 cites W2300779272 @default.
- W3100847195 cites W2340897893 @default.
- W3100847195 cites W2476548250 @default.
- W3100847195 cites W2520707372 @default.
- W3100847195 cites W2609883120 @default.
- W3100847195 cites W2765767940 @default.
- W3100847195 cites W2889061519 @default.
- W3100847195 cites W2913483780 @default.
- W3100847195 cites W2963583471 @default.
- W3100847195 cites W2963652981 @default.
- W3100847195 cites W2963706720 @default.
- W3100847195 cites W2963782415 @default.
- W3100847195 cites W2963906250 @default.
- W3100847195 cites W2964020152 @default.
- W3100847195 cites W2964314455 @default.
- W3100847195 cites W3102327032 @default.
- W3100847195 doi "https://doi.org/10.1109/lra.2019.2925555" @default.
- W3100847195 hasPublicationYear "2019" @default.
- W3100847195 type Work @default.
- W3100847195 sameAs 3100847195 @default.
- W3100847195 citedByCount "47" @default.
- W3100847195 countsByYear W31008471952019 @default.
- W3100847195 countsByYear W31008471952020 @default.
- W3100847195 countsByYear W31008471952021 @default.
- W3100847195 countsByYear W31008471952022 @default.
- W3100847195 countsByYear W31008471952023 @default.
- W3100847195 crossrefType "journal-article" @default.
- W3100847195 hasAuthorship W3100847195A5046559236 @default.
- W3100847195 hasAuthorship W3100847195A5076389260 @default.
- W3100847195 hasBestOaLocation W31008471952 @default.
- W3100847195 hasConcept C10161872 @default.
- W3100847195 hasConcept C104114177 @default.
- W3100847195 hasConcept C108583219 @default.
- W3100847195 hasConcept C153180895 @default.
- W3100847195 hasConcept C154945302 @default.
- W3100847195 hasConcept C2776214188 @default.
- W3100847195 hasConcept C31972630 @default.
- W3100847195 hasConcept C41008148 @default.
- W3100847195 hasConcept C5799516 @default.
- W3100847195 hasConcept C65909025 @default.
- W3100847195 hasConcept C8038995 @default.
- W3100847195 hasConcept C90509273 @default.
- W3100847195 hasConceptScore W3100847195C10161872 @default.
- W3100847195 hasConceptScore W3100847195C104114177 @default.
- W3100847195 hasConceptScore W3100847195C108583219 @default.
- W3100847195 hasConceptScore W3100847195C153180895 @default.
- W3100847195 hasConceptScore W3100847195C154945302 @default.
- W3100847195 hasConceptScore W3100847195C2776214188 @default.
- W3100847195 hasConceptScore W3100847195C31972630 @default.
- W3100847195 hasConceptScore W3100847195C41008148 @default.
- W3100847195 hasConceptScore W3100847195C5799516 @default.
- W3100847195 hasConceptScore W3100847195C65909025 @default.
- W3100847195 hasConceptScore W3100847195C8038995 @default.
- W3100847195 hasConceptScore W3100847195C90509273 @default.
- W3100847195 hasIssue "4" @default.
- W3100847195 hasLocation W31008471951 @default.
- W3100847195 hasLocation W31008471952 @default.
- W3100847195 hasLocation W31008471953 @default.
- W3100847195 hasOpenAccess W3100847195 @default.
- W3100847195 hasPrimaryLocation W31008471951 @default.
- W3100847195 hasRelatedWork W2003315864 @default.
- W3100847195 hasRelatedWork W2126722086 @default.
- W3100847195 hasRelatedWork W2186038791 @default.
- W3100847195 hasRelatedWork W2570368085 @default.
- W3100847195 hasRelatedWork W2767907963 @default.
- W3100847195 hasRelatedWork W2896474523 @default.
- W3100847195 hasRelatedWork W2947241406 @default.
- W3100847195 hasRelatedWork W2971051170 @default.
- W3100847195 hasRelatedWork W3004363006 @default.
- W3100847195 hasRelatedWork W4309676925 @default.
- W3100847195 hasVolume "4" @default.
- W3100847195 isParatext "false" @default.
- W3100847195 isRetracted "false" @default.
- W3100847195 magId "3100847195" @default.
- W3100847195 workType "article" @default.