Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226152092> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4226152092 abstract "Self-supervised learning for monocular depth estimation has been widely investigated as an alternative to the supervised learning approach. Uncertainty estimation in depth estimation is a crucial problem for applications, such as autonomous driving, in detecting unreliable depth. In this study, we propose a variational model to estimate depth uncertainty in self-supervised learning. Our approach leverages time-series images to handle the depth distribution from appearance variations in training. We introduce the Mahalanobis-Wasserstein distance between two consecutive frames to learn the uncertainty. In inference, our method estimates the uncertainty map and the depth image at each pixel from a single image. In experiments on KITTI, Make3D, and DIODE datasets, we show that our model achieves better uncertainty estimation than previous approaches as well as high accuracy of depth estimation" @default.
- W4226152092 created "2022-05-05" @default.
- W4226152092 creator A5009788491 @default.
- W4226152092 creator A5054754593 @default.
- W4226152092 creator A5057238110 @default.
- W4226152092 creator A5069078994 @default.
- W4226152092 date "2021-12-01" @default.
- W4226152092 modified "2023-09-27" @default.
- W4226152092 title "Variational Monocular Depth Estimation for Reliability Prediction" @default.
- W4226152092 cites W2020999234 @default.
- W4226152092 cites W2115579991 @default.
- W4226152092 cites W2130422193 @default.
- W4226152092 cites W2133665775 @default.
- W4226152092 cites W2194775991 @default.
- W4226152092 cites W2336416123 @default.
- W4226152092 cites W2348664362 @default.
- W4226152092 cites W2561074213 @default.
- W4226152092 cites W2609883120 @default.
- W4226152092 cites W2883362496 @default.
- W4226152092 cites W2890949887 @default.
- W4226152092 cites W2963316641 @default.
- W4226152092 cites W2963318716 @default.
- W4226152092 cites W2963412495 @default.
- W4226152092 cites W2963488291 @default.
- W4226152092 cites W2963549785 @default.
- W4226152092 cites W2963583471 @default.
- W4226152092 cites W2963654727 @default.
- W4226152092 cites W2963906250 @default.
- W4226152092 cites W2964968086 @default.
- W4226152092 cites W2967550825 @default.
- W4226152092 cites W2981732213 @default.
- W4226152092 cites W2982102242 @default.
- W4226152092 cites W2985775862 @default.
- W4226152092 cites W2988910664 @default.
- W4226152092 cites W3008061557 @default.
- W4226152092 cites W3034233942 @default.
- W4226152092 cites W3034428934 @default.
- W4226152092 cites W3034475171 @default.
- W4226152092 cites W3034723120 @default.
- W4226152092 cites W3108735274 @default.
- W4226152092 cites W3130567435 @default.
- W4226152092 cites W4206471589 @default.
- W4226152092 doi "https://doi.org/10.1109/3dv53792.2021.00073" @default.
- W4226152092 hasPublicationYear "2021" @default.
- W4226152092 type Work @default.
- W4226152092 citedByCount "2" @default.
- W4226152092 countsByYear W42261520922022 @default.
- W4226152092 crossrefType "proceedings-article" @default.
- W4226152092 hasAuthorship W4226152092A5009788491 @default.
- W4226152092 hasAuthorship W4226152092A5054754593 @default.
- W4226152092 hasAuthorship W4226152092A5057238110 @default.
- W4226152092 hasAuthorship W4226152092A5069078994 @default.
- W4226152092 hasConcept C115961682 @default.
- W4226152092 hasConcept C119857082 @default.
- W4226152092 hasConcept C121332964 @default.
- W4226152092 hasConcept C127413603 @default.
- W4226152092 hasConcept C153180895 @default.
- W4226152092 hasConcept C154945302 @default.
- W4226152092 hasConcept C163258240 @default.
- W4226152092 hasConcept C1921717 @default.
- W4226152092 hasConcept C201995342 @default.
- W4226152092 hasConcept C2776214188 @default.
- W4226152092 hasConcept C31972630 @default.
- W4226152092 hasConcept C41008148 @default.
- W4226152092 hasConcept C43214815 @default.
- W4226152092 hasConcept C62520636 @default.
- W4226152092 hasConcept C65909025 @default.
- W4226152092 hasConcept C96250715 @default.
- W4226152092 hasConceptScore W4226152092C115961682 @default.
- W4226152092 hasConceptScore W4226152092C119857082 @default.
- W4226152092 hasConceptScore W4226152092C121332964 @default.
- W4226152092 hasConceptScore W4226152092C127413603 @default.
- W4226152092 hasConceptScore W4226152092C153180895 @default.
- W4226152092 hasConceptScore W4226152092C154945302 @default.
- W4226152092 hasConceptScore W4226152092C163258240 @default.
- W4226152092 hasConceptScore W4226152092C1921717 @default.
- W4226152092 hasConceptScore W4226152092C201995342 @default.
- W4226152092 hasConceptScore W4226152092C2776214188 @default.
- W4226152092 hasConceptScore W4226152092C31972630 @default.
- W4226152092 hasConceptScore W4226152092C41008148 @default.
- W4226152092 hasConceptScore W4226152092C43214815 @default.
- W4226152092 hasConceptScore W4226152092C62520636 @default.
- W4226152092 hasConceptScore W4226152092C65909025 @default.
- W4226152092 hasConceptScore W4226152092C96250715 @default.
- W4226152092 hasLocation W42261520921 @default.
- W4226152092 hasOpenAccess W4226152092 @default.
- W4226152092 hasPrimaryLocation W42261520921 @default.
- W4226152092 hasRelatedWork W127013308 @default.
- W4226152092 hasRelatedWork W1628937209 @default.
- W4226152092 hasRelatedWork W1881882553 @default.
- W4226152092 hasRelatedWork W2094957557 @default.
- W4226152092 hasRelatedWork W2113039159 @default.
- W4226152092 hasRelatedWork W3006563365 @default.
- W4226152092 hasRelatedWork W4224011692 @default.
- W4226152092 hasRelatedWork W4225827157 @default.
- W4226152092 hasRelatedWork W4292794826 @default.
- W4226152092 hasRelatedWork W4321512589 @default.
- W4226152092 isParatext "false" @default.
- W4226152092 isRetracted "false" @default.
- W4226152092 workType "article" @default.