Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285102356> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4285102356 abstract "Monocular depth estimation in the wild inherently predicts depth up to an unknown scale. To resolve scale ambiguity issue, we present a learning algorithm that leverages monocular simultaneous localization and mapping (SLAM) with proprioceptive sensors. Such monocular SLAM systems can provide metrically scaled camera poses. Given these metric poses and monocular sequences, we propose a self-supervised learning method for the pre-trained supervised monocular depth networks to enable metrically scaled depth estimation. Our approach is based on a teacher-student formulation which guides our network to predict high-quality depths. We demonstrate that our approach is useful for various applications such as mobile robot navigation and is applicable to diverse environments. Our full system shows improvements over recent self-supervised depth estimation and completion methods on EuRoC, OpenLORIS, and ScanNet datasets." @default.
- W4285102356 created "2022-07-14" @default.
- W4285102356 creator A5004194238 @default.
- W4285102356 creator A5004215103 @default.
- W4285102356 creator A5016968299 @default.
- W4285102356 creator A5027028606 @default.
- W4285102356 creator A5055858656 @default.
- W4285102356 creator A5086277177 @default.
- W4285102356 date "2022-05-23" @default.
- W4285102356 modified "2023-09-24" @default.
- W4285102356 title "SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning" @default.
- W4285102356 cites W2118223742 @default.
- W4285102356 cites W2133665775 @default.
- W4285102356 cites W2194775991 @default.
- W4285102356 cites W2396274919 @default.
- W4285102356 cites W2482726005 @default.
- W4285102356 cites W2549139847 @default.
- W4285102356 cites W2594519801 @default.
- W4285102356 cites W2736960679 @default.
- W4285102356 cites W2745859992 @default.
- W4285102356 cites W2883702102 @default.
- W4285102356 cites W2883923125 @default.
- W4285102356 cites W2963412495 @default.
- W4285102356 cites W2963488291 @default.
- W4285102356 cites W2963760790 @default.
- W4285102356 cites W2969202876 @default.
- W4285102356 cites W2982336692 @default.
- W4285102356 cites W2985775862 @default.
- W4285102356 cites W2998031326 @default.
- W4285102356 cites W3000500950 @default.
- W4285102356 cites W3003796433 @default.
- W4285102356 cites W3034604951 @default.
- W4285102356 cites W3034726754 @default.
- W4285102356 cites W3035563424 @default.
- W4285102356 cites W3048510980 @default.
- W4285102356 cites W3081167590 @default.
- W4285102356 cites W3084438944 @default.
- W4285102356 cites W3089936780 @default.
- W4285102356 cites W3090386798 @default.
- W4285102356 cites W3103648783 @default.
- W4285102356 cites W3124420883 @default.
- W4285102356 cites W3129248413 @default.
- W4285102356 cites W3129944514 @default.
- W4285102356 cites W3130800379 @default.
- W4285102356 cites W3132983546 @default.
- W4285102356 cites W3145284865 @default.
- W4285102356 cites W3174458495 @default.
- W4285102356 cites W3191778791 @default.
- W4285102356 cites W3205553412 @default.
- W4285102356 cites W3206399213 @default.
- W4285102356 doi "https://doi.org/10.1109/icra46639.2022.9811639" @default.
- W4285102356 hasPublicationYear "2022" @default.
- W4285102356 type Work @default.
- W4285102356 citedByCount "2" @default.
- W4285102356 countsByYear W42851023562023 @default.
- W4285102356 crossrefType "proceedings-article" @default.
- W4285102356 hasAuthorship W4285102356A5004194238 @default.
- W4285102356 hasAuthorship W4285102356A5004215103 @default.
- W4285102356 hasAuthorship W4285102356A5016968299 @default.
- W4285102356 hasAuthorship W4285102356A5027028606 @default.
- W4285102356 hasAuthorship W4285102356A5055858656 @default.
- W4285102356 hasAuthorship W4285102356A5086277177 @default.
- W4285102356 hasBestOaLocation W42851023562 @default.
- W4285102356 hasConcept C127413603 @default.
- W4285102356 hasConcept C154945302 @default.
- W4285102356 hasConcept C201995342 @default.
- W4285102356 hasConcept C31972630 @default.
- W4285102356 hasConcept C41008148 @default.
- W4285102356 hasConcept C65909025 @default.
- W4285102356 hasConcept C96250715 @default.
- W4285102356 hasConceptScore W4285102356C127413603 @default.
- W4285102356 hasConceptScore W4285102356C154945302 @default.
- W4285102356 hasConceptScore W4285102356C201995342 @default.
- W4285102356 hasConceptScore W4285102356C31972630 @default.
- W4285102356 hasConceptScore W4285102356C41008148 @default.
- W4285102356 hasConceptScore W4285102356C65909025 @default.
- W4285102356 hasConceptScore W4285102356C96250715 @default.
- W4285102356 hasFunder F4320324891 @default.
- W4285102356 hasLocation W42851023561 @default.
- W4285102356 hasLocation W42851023562 @default.
- W4285102356 hasOpenAccess W4285102356 @default.
- W4285102356 hasPrimaryLocation W42851023561 @default.
- W4285102356 isParatext "false" @default.
- W4285102356 isRetracted "false" @default.
- W4285102356 workType "article" @default.