Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100901464> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3100901464 abstract "In the last decade, supervised deep learning approaches have been extensively employed in visual odometry (VO) applications, which is not feasible in environments where labelled data is not abundant. On the other hand, unsupervised deep learning approaches for localization and mapping in unknown environments from unlabelled data have received comparatively less attention in VO research. In this study, we propose a generative unsupervised learning framework that predicts 6-DoF pose camera motion and monocular depth map of the scene from unlabelled RGB image sequences, using deep convolutional Generative Adversarial Networks (GANs). We create a supervisory signal by warping view sequences and assigning the re-projection minimization to the objective loss function that is adopted in multi-view pose estimation and single-view depth generation network. Detailed quantitative and qualitative evaluations of the proposed framework on the KITTI [1] and Cityscapes [2] datasets show that the proposed method outperforms both existing traditional and unsupervised deep VO methods providing better results for both pose estimation and depth recovery." @default.
- W3100901464 created "2020-11-23" @default.
- W3100901464 creator A5010637110 @default.
- W3100901464 creator A5020331930 @default.
- W3100901464 creator A5030156598 @default.
- W3100901464 creator A5060183988 @default.
- W3100901464 creator A5077645636 @default.
- W3100901464 date "2019-05-01" @default.
- W3100901464 modified "2023-09-24" @default.
- W3100901464 title "GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks" @default.
- W3100901464 cites W1573897183 @default.
- W3100901464 cites W1803059841 @default.
- W3100901464 cites W1921093919 @default.
- W3100901464 cites W2008706659 @default.
- W3100901464 cites W2016416397 @default.
- W3100901464 cites W2071499765 @default.
- W3100901464 cites W2108134361 @default.
- W3100901464 cites W2113014142 @default.
- W3100901464 cites W2150066425 @default.
- W3100901464 cites W2151290401 @default.
- W3100901464 cites W2340897893 @default.
- W3100901464 cites W2411454842 @default.
- W3100901464 cites W2520707372 @default.
- W3100901464 cites W2598706937 @default.
- W3100901464 cites W2609883120 @default.
- W3100901464 cites W2612774882 @default.
- W3100901464 cites W2745549613 @default.
- W3100901464 cites W2751326577 @default.
- W3100901464 cites W2768662421 @default.
- W3100901464 cites W2788608285 @default.
- W3100901464 cites W2962891637 @default.
- W3100901464 cites W2962915388 @default.
- W3100901464 cites W2963583471 @default.
- W3100901464 cites W2963596017 @default.
- W3100901464 cites W3102327032 @default.
- W3100901464 cites W3103648783 @default.
- W3100901464 doi "https://doi.org/10.1109/icra.2019.8793512" @default.
- W3100901464 hasPublicationYear "2019" @default.
- W3100901464 type Work @default.
- W3100901464 sameAs 3100901464 @default.
- W3100901464 citedByCount "106" @default.
- W3100901464 countsByYear W31009014642019 @default.
- W3100901464 countsByYear W31009014642020 @default.
- W3100901464 countsByYear W31009014642021 @default.
- W3100901464 countsByYear W31009014642022 @default.
- W3100901464 countsByYear W31009014642023 @default.
- W3100901464 crossrefType "proceedings-article" @default.
- W3100901464 hasAuthorship W3100901464A5010637110 @default.
- W3100901464 hasAuthorship W3100901464A5020331930 @default.
- W3100901464 hasAuthorship W3100901464A5030156598 @default.
- W3100901464 hasAuthorship W3100901464A5060183988 @default.
- W3100901464 hasAuthorship W3100901464A5077645636 @default.
- W3100901464 hasBestOaLocation W31009014642 @default.
- W3100901464 hasConcept C108583219 @default.
- W3100901464 hasConcept C153180895 @default.
- W3100901464 hasConcept C154945302 @default.
- W3100901464 hasConcept C157202957 @default.
- W3100901464 hasConcept C31972630 @default.
- W3100901464 hasConcept C41008148 @default.
- W3100901464 hasConcept C52102323 @default.
- W3100901464 hasConcept C5799516 @default.
- W3100901464 hasConcept C65909025 @default.
- W3100901464 hasConcept C8038995 @default.
- W3100901464 hasConcept C81363708 @default.
- W3100901464 hasConcept C90509273 @default.
- W3100901464 hasConceptScore W3100901464C108583219 @default.
- W3100901464 hasConceptScore W3100901464C153180895 @default.
- W3100901464 hasConceptScore W3100901464C154945302 @default.
- W3100901464 hasConceptScore W3100901464C157202957 @default.
- W3100901464 hasConceptScore W3100901464C31972630 @default.
- W3100901464 hasConceptScore W3100901464C41008148 @default.
- W3100901464 hasConceptScore W3100901464C52102323 @default.
- W3100901464 hasConceptScore W3100901464C5799516 @default.
- W3100901464 hasConceptScore W3100901464C65909025 @default.
- W3100901464 hasConceptScore W3100901464C8038995 @default.
- W3100901464 hasConceptScore W3100901464C81363708 @default.
- W3100901464 hasConceptScore W3100901464C90509273 @default.
- W3100901464 hasLocation W31009014641 @default.
- W3100901464 hasLocation W31009014642 @default.
- W3100901464 hasLocation W31009014643 @default.
- W3100901464 hasOpenAccess W3100901464 @default.
- W3100901464 hasPrimaryLocation W31009014641 @default.
- W3100901464 hasRelatedWork W197633916 @default.
- W3100901464 hasRelatedWork W2767907963 @default.
- W3100901464 hasRelatedWork W2962781507 @default.
- W3100901464 hasRelatedWork W2970134868 @default.
- W3100901464 hasRelatedWork W2973104315 @default.
- W3100901464 hasRelatedWork W3121134787 @default.
- W3100901464 hasRelatedWork W3138755061 @default.
- W3100901464 hasRelatedWork W4200630066 @default.
- W3100901464 hasRelatedWork W4226256580 @default.
- W3100901464 hasRelatedWork W4289543137 @default.
- W3100901464 isParatext "false" @default.
- W3100901464 isRetracted "false" @default.
- W3100901464 magId "3100901464" @default.
- W3100901464 workType "article" @default.