Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312903731> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4312903731 abstract "Estimating a semantically segmented bird's-eye-view (BEV) map from a single image has become a popular technique for autonomous control and navigation. However, they show an increase in localization error with distance from the camera. While such an increase in error is entirely expected -localization is harder at distance - much of the drop in performance can be attributed to the cues used by current texture-based models, in particular, they make heavy use of object-ground intersections (such as shadows) [10], which become increasingly sparse and uncertain for distant objects. In this work, we address these shortcomings in BEV-mapping by learning the spatial relationship between objects in a scene. We propose a graph neural network which predicts BEV objects from a monocular image by spatially reasoning about an object within the context of other objects. Our approach sets a new state-of-the-art in BEV estimation from monocular images across three large-scale datasets, including a 50% relative improvement for objects on nuScenes." @default.
- W4312903731 created "2023-01-05" @default.
- W4312903731 creator A5008943199 @default.
- W4312903731 creator A5010512009 @default.
- W4312903731 creator A5033644268 @default.
- W4312903731 creator A5044490167 @default.
- W4312903731 date "2022-06-01" @default.
- W4312903731 modified "2023-10-16" @default.
- W4312903731 title "'The Pedestrian next to the Lamppost” Adaptive Object Graphs for Better Instantaneous Mapping" @default.
- W4312903731 cites W1536680647 @default.
- W4312903731 cites W2054389289 @default.
- W4312903731 cites W2194775991 @default.
- W4312903731 cites W2468368736 @default.
- W4312903731 cites W2560544142 @default.
- W4312903731 cites W2594183968 @default.
- W4312903731 cites W2799215407 @default.
- W4312903731 cites W2890003176 @default.
- W4312903731 cites W2948515602 @default.
- W4312903731 cites W2955189650 @default.
- W4312903731 cites W2963323244 @default.
- W4312903731 cites W2963351448 @default.
- W4312903731 cites W2963364380 @default.
- W4312903731 cites W2964249569 @default.
- W4312903731 cites W2970562905 @default.
- W4312903731 cites W2981353488 @default.
- W4312903731 cites W2981857055 @default.
- W4312903731 cites W3003639745 @default.
- W4312903731 cites W3007309629 @default.
- W4312903731 cites W3034479628 @default.
- W4312903731 cites W3034669477 @default.
- W4312903731 cites W3034868890 @default.
- W4312903731 cites W3093002101 @default.
- W4312903731 cites W3205150709 @default.
- W4312903731 cites W3215100485 @default.
- W4312903731 doi "https://doi.org/10.1109/cvpr52688.2022.01892" @default.
- W4312903731 hasPublicationYear "2022" @default.
- W4312903731 type Work @default.
- W4312903731 citedByCount "1" @default.
- W4312903731 crossrefType "proceedings-article" @default.
- W4312903731 hasAuthorship W4312903731A5008943199 @default.
- W4312903731 hasAuthorship W4312903731A5010512009 @default.
- W4312903731 hasAuthorship W4312903731A5033644268 @default.
- W4312903731 hasAuthorship W4312903731A5044490167 @default.
- W4312903731 hasBestOaLocation W43129037312 @default.
- W4312903731 hasConcept C146849305 @default.
- W4312903731 hasConcept C153180895 @default.
- W4312903731 hasConcept C154945302 @default.
- W4312903731 hasConcept C166957645 @default.
- W4312903731 hasConcept C205649164 @default.
- W4312903731 hasConcept C2776151529 @default.
- W4312903731 hasConcept C2779343474 @default.
- W4312903731 hasConcept C2781238097 @default.
- W4312903731 hasConcept C31972630 @default.
- W4312903731 hasConcept C41008148 @default.
- W4312903731 hasConcept C64754055 @default.
- W4312903731 hasConcept C65909025 @default.
- W4312903731 hasConceptScore W4312903731C146849305 @default.
- W4312903731 hasConceptScore W4312903731C153180895 @default.
- W4312903731 hasConceptScore W4312903731C154945302 @default.
- W4312903731 hasConceptScore W4312903731C166957645 @default.
- W4312903731 hasConceptScore W4312903731C205649164 @default.
- W4312903731 hasConceptScore W4312903731C2776151529 @default.
- W4312903731 hasConceptScore W4312903731C2779343474 @default.
- W4312903731 hasConceptScore W4312903731C2781238097 @default.
- W4312903731 hasConceptScore W4312903731C31972630 @default.
- W4312903731 hasConceptScore W4312903731C41008148 @default.
- W4312903731 hasConceptScore W4312903731C64754055 @default.
- W4312903731 hasConceptScore W4312903731C65909025 @default.
- W4312903731 hasLocation W43129037311 @default.
- W4312903731 hasLocation W43129037312 @default.
- W4312903731 hasLocation W43129037313 @default.
- W4312903731 hasOpenAccess W4312903731 @default.
- W4312903731 hasPrimaryLocation W43129037311 @default.
- W4312903731 hasRelatedWork W1991834176 @default.
- W4312903731 hasRelatedWork W200819717 @default.
- W4312903731 hasRelatedWork W2032269556 @default.
- W4312903731 hasRelatedWork W2063823869 @default.
- W4312903731 hasRelatedWork W2064421702 @default.
- W4312903731 hasRelatedWork W2885323543 @default.
- W4312903731 hasRelatedWork W2944448661 @default.
- W4312903731 hasRelatedWork W3034732808 @default.
- W4312903731 hasRelatedWork W4292830139 @default.
- W4312903731 hasRelatedWork W4295532600 @default.
- W4312903731 isParatext "false" @default.
- W4312903731 isRetracted "false" @default.
- W4312903731 workType "article" @default.