Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312973344> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4312973344 abstract "Learning-based depth estimation has witnessed recent progress in multiple directions; from self-supervision using monocular video to supervised methods offering highest accuracy. Complementary to supervision, further boosts to performance and robustness are gained by combining information from multiple signals. In this paper we systematically investigate key trade-offs associated with sensor and modality design choices as well as related model training strategies. Our study leads us to a new method, capable of connecting modality-specific advantages from polarisation, Time-of-Flight and structured-light inputs. We propose a novel pipeline capable of estimating depth from monocular polarisation for which we evaluate various training signals. The inversion of differentiable analytic models thereby connects scene geometry with polarisation and ToF signals and enables self-supervised and cross-modal learning. In the absence of existing multimodal datasets, we examine our approach with a custom-made multi-modal camera rig and collect CroMo; the first dataset to consist of synchronized stereo polarisation, indirect ToF and structured-light depth, captured at video rates. Extensive experiments on challenging video scenes confirm both qualitative and quantitative pipeline advantages where we are able to outperform competitive monocular depth estimation methods." @default.
- W4312973344 created "2023-01-05" @default.
- W4312973344 creator A5024498176 @default.
- W4312973344 creator A5046874089 @default.
- W4312973344 creator A5052824649 @default.
- W4312973344 creator A5067135033 @default.
- W4312973344 creator A5072008141 @default.
- W4312973344 creator A5085971943 @default.
- W4312973344 date "2022-06-01" @default.
- W4312973344 modified "2023-10-18" @default.
- W4312973344 title "CroMo: Cross-Modal Learning for Monocular Depth Estimation" @default.
- W4312973344 doi "https://doi.org/10.1109/cvpr52688.2022.00391" @default.
- W4312973344 hasPublicationYear "2022" @default.
- W4312973344 type Work @default.
- W4312973344 citedByCount "4" @default.
- W4312973344 countsByYear W43129733442022 @default.
- W4312973344 countsByYear W43129733442023 @default.
- W4312973344 crossrefType "proceedings-article" @default.
- W4312973344 hasAuthorship W4312973344A5024498176 @default.
- W4312973344 hasAuthorship W4312973344A5046874089 @default.
- W4312973344 hasAuthorship W4312973344A5052824649 @default.
- W4312973344 hasAuthorship W4312973344A5067135033 @default.
- W4312973344 hasAuthorship W4312973344A5072008141 @default.
- W4312973344 hasAuthorship W4312973344A5085971943 @default.
- W4312973344 hasBestOaLocation W43129733442 @default.
- W4312973344 hasConcept C104317684 @default.
- W4312973344 hasConcept C109007969 @default.
- W4312973344 hasConcept C127313418 @default.
- W4312973344 hasConcept C151730666 @default.
- W4312973344 hasConcept C154945302 @default.
- W4312973344 hasConcept C185592680 @default.
- W4312973344 hasConcept C188027245 @default.
- W4312973344 hasConcept C1893757 @default.
- W4312973344 hasConcept C193581530 @default.
- W4312973344 hasConcept C199360897 @default.
- W4312973344 hasConcept C2780226545 @default.
- W4312973344 hasConcept C31972630 @default.
- W4312973344 hasConcept C41008148 @default.
- W4312973344 hasConcept C43521106 @default.
- W4312973344 hasConcept C55493867 @default.
- W4312973344 hasConcept C63479239 @default.
- W4312973344 hasConcept C65909025 @default.
- W4312973344 hasConcept C71139939 @default.
- W4312973344 hasConceptScore W4312973344C104317684 @default.
- W4312973344 hasConceptScore W4312973344C109007969 @default.
- W4312973344 hasConceptScore W4312973344C127313418 @default.
- W4312973344 hasConceptScore W4312973344C151730666 @default.
- W4312973344 hasConceptScore W4312973344C154945302 @default.
- W4312973344 hasConceptScore W4312973344C185592680 @default.
- W4312973344 hasConceptScore W4312973344C188027245 @default.
- W4312973344 hasConceptScore W4312973344C1893757 @default.
- W4312973344 hasConceptScore W4312973344C193581530 @default.
- W4312973344 hasConceptScore W4312973344C199360897 @default.
- W4312973344 hasConceptScore W4312973344C2780226545 @default.
- W4312973344 hasConceptScore W4312973344C31972630 @default.
- W4312973344 hasConceptScore W4312973344C41008148 @default.
- W4312973344 hasConceptScore W4312973344C43521106 @default.
- W4312973344 hasConceptScore W4312973344C55493867 @default.
- W4312973344 hasConceptScore W4312973344C63479239 @default.
- W4312973344 hasConceptScore W4312973344C65909025 @default.
- W4312973344 hasConceptScore W4312973344C71139939 @default.
- W4312973344 hasLocation W43129733441 @default.
- W4312973344 hasLocation W43129733442 @default.
- W4312973344 hasLocation W43129733443 @default.
- W4312973344 hasLocation W43129733444 @default.
- W4312973344 hasOpenAccess W4312973344 @default.
- W4312973344 hasPrimaryLocation W43129733441 @default.
- W4312973344 hasRelatedWork W127013308 @default.
- W4312973344 hasRelatedWork W1628937209 @default.
- W4312973344 hasRelatedWork W2035976912 @default.
- W4312973344 hasRelatedWork W2094957557 @default.
- W4312973344 hasRelatedWork W2113039159 @default.
- W4312973344 hasRelatedWork W2541791370 @default.
- W4312973344 hasRelatedWork W2971051170 @default.
- W4312973344 hasRelatedWork W3185738386 @default.
- W4312973344 hasRelatedWork W4224011692 @default.
- W4312973344 hasRelatedWork W4321512589 @default.
- W4312973344 isParatext "false" @default.
- W4312973344 isRetracted "false" @default.
- W4312973344 workType "article" @default.