Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280522017> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4280522017 endingPage "78" @default.
- W4280522017 startingPage "69" @default.
- W4280522017 abstract "Abstract. The necessity to identify errors in the context of image-based 3D reconstruction has motivated the development of various methods for the estimation of uncertainty associated with depth estimates in recent years. Most of these methods exclusively estimate aleatoric uncertainty, which describes stochastic effects. On the other hand, epistemic uncertainty, which accounts for simplifications or incorrect assumptions with respect to the formulated model hypothesis, is often neglected. However, to accurately quantify the uncertainty inherent in a process, it is necessary to consider all potential sources of uncertainty and to model their stochastic behaviour appropriately. To approach this objective, a holistic method to jointly estimate disparity and uncertainty is presented in this work, taking into account both aleatoric and epistemic uncertainty. For this purpose, the proposed method is based on a Bayesian Neural Network, which is trained with variational inference using a probabilistic loss formulation. To evaluate the performance of the method proposed, extensive experiments are carried out on three datasets considering real-world indoor and outdoor scenes. The results of these experiments demonstrate that the proposed method is able to estimate the uncertainty accurately, while showing a similar and for some scenarios improved depth estimation capability compared to the dense stereo matching approach used as deterministic baseline. Moreover, the evaluation reveals the importance of considering both, aleatoric and epistemic uncertainty, in order to achieve an accurate estimation of the overall uncertainty related to a depth estimate." @default.
- W4280522017 created "2022-05-22" @default.
- W4280522017 creator A5000550463 @default.
- W4280522017 date "2022-05-17" @default.
- W4280522017 modified "2023-09-30" @default.
- W4280522017 title "JOINT ESTIMATION OF DEPTH AND ITS UNCERTAINTY FROM STEREO IMAGES USING BAYESIAN DEEP LEARNING" @default.
- W4280522017 doi "https://doi.org/10.5194/isprs-annals-v-2-2022-69-2022" @default.
- W4280522017 hasPublicationYear "2022" @default.
- W4280522017 type Work @default.
- W4280522017 citedByCount "1" @default.
- W4280522017 countsByYear W42805220172023 @default.
- W4280522017 crossrefType "journal-article" @default.
- W4280522017 hasAuthorship W4280522017A5000550463 @default.
- W4280522017 hasBestOaLocation W42805220171 @default.
- W4280522017 hasConcept C105795698 @default.
- W4280522017 hasConcept C107673813 @default.
- W4280522017 hasConcept C111368507 @default.
- W4280522017 hasConcept C111919701 @default.
- W4280522017 hasConcept C119857082 @default.
- W4280522017 hasConcept C12725497 @default.
- W4280522017 hasConcept C127313418 @default.
- W4280522017 hasConcept C127413603 @default.
- W4280522017 hasConcept C137209882 @default.
- W4280522017 hasConcept C144024400 @default.
- W4280522017 hasConcept C151730666 @default.
- W4280522017 hasConcept C154945302 @default.
- W4280522017 hasConcept C160234255 @default.
- W4280522017 hasConcept C165064840 @default.
- W4280522017 hasConcept C176147448 @default.
- W4280522017 hasConcept C177803969 @default.
- W4280522017 hasConcept C201995342 @default.
- W4280522017 hasConcept C2776214188 @default.
- W4280522017 hasConcept C2779343474 @default.
- W4280522017 hasConcept C32230216 @default.
- W4280522017 hasConcept C33923547 @default.
- W4280522017 hasConcept C41008148 @default.
- W4280522017 hasConcept C44154836 @default.
- W4280522017 hasConcept C46312422 @default.
- W4280522017 hasConcept C49937458 @default.
- W4280522017 hasConcept C86803240 @default.
- W4280522017 hasConcept C94361409 @default.
- W4280522017 hasConcept C96250715 @default.
- W4280522017 hasConcept C98045186 @default.
- W4280522017 hasConceptScore W4280522017C105795698 @default.
- W4280522017 hasConceptScore W4280522017C107673813 @default.
- W4280522017 hasConceptScore W4280522017C111368507 @default.
- W4280522017 hasConceptScore W4280522017C111919701 @default.
- W4280522017 hasConceptScore W4280522017C119857082 @default.
- W4280522017 hasConceptScore W4280522017C12725497 @default.
- W4280522017 hasConceptScore W4280522017C127313418 @default.
- W4280522017 hasConceptScore W4280522017C127413603 @default.
- W4280522017 hasConceptScore W4280522017C137209882 @default.
- W4280522017 hasConceptScore W4280522017C144024400 @default.
- W4280522017 hasConceptScore W4280522017C151730666 @default.
- W4280522017 hasConceptScore W4280522017C154945302 @default.
- W4280522017 hasConceptScore W4280522017C160234255 @default.
- W4280522017 hasConceptScore W4280522017C165064840 @default.
- W4280522017 hasConceptScore W4280522017C176147448 @default.
- W4280522017 hasConceptScore W4280522017C177803969 @default.
- W4280522017 hasConceptScore W4280522017C201995342 @default.
- W4280522017 hasConceptScore W4280522017C2776214188 @default.
- W4280522017 hasConceptScore W4280522017C2779343474 @default.
- W4280522017 hasConceptScore W4280522017C32230216 @default.
- W4280522017 hasConceptScore W4280522017C33923547 @default.
- W4280522017 hasConceptScore W4280522017C41008148 @default.
- W4280522017 hasConceptScore W4280522017C44154836 @default.
- W4280522017 hasConceptScore W4280522017C46312422 @default.
- W4280522017 hasConceptScore W4280522017C49937458 @default.
- W4280522017 hasConceptScore W4280522017C86803240 @default.
- W4280522017 hasConceptScore W4280522017C94361409 @default.
- W4280522017 hasConceptScore W4280522017C96250715 @default.
- W4280522017 hasConceptScore W4280522017C98045186 @default.
- W4280522017 hasLocation W42805220171 @default.
- W4280522017 hasOpenAccess W4280522017 @default.
- W4280522017 hasPrimaryLocation W42805220171 @default.
- W4280522017 hasRelatedWork W1489922926 @default.
- W4280522017 hasRelatedWork W1574051301 @default.
- W4280522017 hasRelatedWork W192625647 @default.
- W4280522017 hasRelatedWork W2031920515 @default.
- W4280522017 hasRelatedWork W2106991107 @default.
- W4280522017 hasRelatedWork W2224641141 @default.
- W4280522017 hasRelatedWork W3113975374 @default.
- W4280522017 hasRelatedWork W3175794431 @default.
- W4280522017 hasRelatedWork W3176993129 @default.
- W4280522017 hasRelatedWork W4376309286 @default.
- W4280522017 hasVolume "V-2-2022" @default.
- W4280522017 isParatext "false" @default.
- W4280522017 isRetracted "false" @default.
- W4280522017 workType "article" @default.