Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312693760> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4312693760 abstract "Visual odometry (VO) and single image depth estimation are critical for robot vision, 3D reconstruction, and camera pose estimation that can be applied to autonomous driving, map building, augmented reality and many other applications. Various supervised learning models have been proposed to train the VO or single image depth estimation framework for each targeted scene to improve the performance recently. However, little effort has been made to learn these separate tasks together without requiring the collection of a significant number of labels. This paper proposes a novel unsupervised learning approach to simultaneously perceive VO and single image depth estimation. In our framework, either of these tasks can benefit from each other through simultaneously learning these two tasks. We correlate these two tasks by enforcing depth consistency between VO and single image depth estimation. Based on the single image depth estimation, we can resolve the most common and challenging scaling issue of monocular VO. Meanwhile, through training from a sequence of images, VO can enhance the single image depth estimation accuracy. The effectiveness of our proposed method is demonstrated through extensive experiments compared with current state-of-the-art methods on the benchmark datasets." @default.
- W4312693760 created "2023-01-05" @default.
- W4312693760 creator A5038578019 @default.
- W4312693760 creator A5085861598 @default.
- W4312693760 date "2022-07-18" @default.
- W4312693760 modified "2023-10-01" @default.
- W4312693760 title "An Unsupervised Approach for Simultaneous Visual Odometry and Single Image Depth Estimation" @default.
- W4312693760 doi "https://doi.org/10.1109/ijcnn55064.2022.9892294" @default.
- W4312693760 hasPublicationYear "2022" @default.
- W4312693760 type Work @default.
- W4312693760 citedByCount "0" @default.
- W4312693760 crossrefType "proceedings-article" @default.
- W4312693760 hasAuthorship W4312693760A5038578019 @default.
- W4312693760 hasAuthorship W4312693760A5085861598 @default.
- W4312693760 hasConcept C115961682 @default.
- W4312693760 hasConcept C127413603 @default.
- W4312693760 hasConcept C13280743 @default.
- W4312693760 hasConcept C141268832 @default.
- W4312693760 hasConcept C153180895 @default.
- W4312693760 hasConcept C153715457 @default.
- W4312693760 hasConcept C154945302 @default.
- W4312693760 hasConcept C185798385 @default.
- W4312693760 hasConcept C201995342 @default.
- W4312693760 hasConcept C205649164 @default.
- W4312693760 hasConcept C2776436953 @default.
- W4312693760 hasConcept C31972630 @default.
- W4312693760 hasConcept C41008148 @default.
- W4312693760 hasConcept C52102323 @default.
- W4312693760 hasConcept C5799516 @default.
- W4312693760 hasConcept C65909025 @default.
- W4312693760 hasConcept C8038995 @default.
- W4312693760 hasConcept C90509273 @default.
- W4312693760 hasConcept C96250715 @default.
- W4312693760 hasConceptScore W4312693760C115961682 @default.
- W4312693760 hasConceptScore W4312693760C127413603 @default.
- W4312693760 hasConceptScore W4312693760C13280743 @default.
- W4312693760 hasConceptScore W4312693760C141268832 @default.
- W4312693760 hasConceptScore W4312693760C153180895 @default.
- W4312693760 hasConceptScore W4312693760C153715457 @default.
- W4312693760 hasConceptScore W4312693760C154945302 @default.
- W4312693760 hasConceptScore W4312693760C185798385 @default.
- W4312693760 hasConceptScore W4312693760C201995342 @default.
- W4312693760 hasConceptScore W4312693760C205649164 @default.
- W4312693760 hasConceptScore W4312693760C2776436953 @default.
- W4312693760 hasConceptScore W4312693760C31972630 @default.
- W4312693760 hasConceptScore W4312693760C41008148 @default.
- W4312693760 hasConceptScore W4312693760C52102323 @default.
- W4312693760 hasConceptScore W4312693760C5799516 @default.
- W4312693760 hasConceptScore W4312693760C65909025 @default.
- W4312693760 hasConceptScore W4312693760C8038995 @default.
- W4312693760 hasConceptScore W4312693760C90509273 @default.
- W4312693760 hasConceptScore W4312693760C96250715 @default.
- W4312693760 hasFunder F4320306076 @default.
- W4312693760 hasLocation W43126937601 @default.
- W4312693760 hasOpenAccess W4312693760 @default.
- W4312693760 hasPrimaryLocation W43126937601 @default.
- W4312693760 hasRelatedWork W2586404362 @default.
- W4312693760 hasRelatedWork W2610028676 @default.
- W4312693760 hasRelatedWork W2757468587 @default.
- W4312693760 hasRelatedWork W2789598255 @default.
- W4312693760 hasRelatedWork W2962781507 @default.
- W4312693760 hasRelatedWork W2973104315 @default.
- W4312693760 hasRelatedWork W3090894413 @default.
- W4312693760 hasRelatedWork W3138755061 @default.
- W4312693760 hasRelatedWork W3173731353 @default.
- W4312693760 hasRelatedWork W4309676925 @default.
- W4312693760 isParatext "false" @default.
- W4312693760 isRetracted "false" @default.
- W4312693760 workType "article" @default.