Matches in SemOpenAlex for { <https://semopenalex.org/work/W2225956744> ?p ?o ?g. }
- W2225956744 abstract "Contextual information can have a substantial impact on the performance of visual tasks such as semantic segmentation, object detection, and geometric estimation. Data stored in Geographic Information Systems (GIS) offers a rich source of contextual information that has been largely untapped by computer vision. We propose to leverage such information for scene understanding by combining GIS resources with large sets of unorganized photographs using Structure from Motion (SfM) techniques. We present a pipeline to quickly generate strong 3D geometric priors from 2D GIS data using SfM models aligned with minimal user input. Given an image resectioned against this model, we generate robust predictions of depth, surface normals, and semantic labels. We show that the precision of the predicted geometry is substantially more accurate other single-image depth estimation methods. We then demonstrate the utility of these contextual constraints for re-scoring pedestrian detections, and use these GIS contextual features alongside object detection score maps to improve a CRF-based semantic segmentation framework, boosting accuracy over baseline models." @default.
- W2225956744 created "2016-06-24" @default.
- W2225956744 creator A5039389241 @default.
- W2225956744 creator A5044978076 @default.
- W2225956744 creator A5064961741 @default.
- W2225956744 creator A5084937810 @default.
- W2225956744 date "2015-07-14" @default.
- W2225956744 modified "2023-09-27" @default.
- W2225956744 title "Lifting GIS Maps into Strong Geometric Context for Scene Understanding" @default.
- W2225956744 cites W109304646 @default.
- W2225956744 cites W148361626 @default.
- W2225956744 cites W1528789833 @default.
- W2225956744 cites W1565402342 @default.
- W2225956744 cites W1610707153 @default.
- W2225956744 cites W1616969904 @default.
- W2225956744 cites W1818727054 @default.
- W2225956744 cites W19582845 @default.
- W2225956744 cites W1962921203 @default.
- W2225956744 cites W1964005749 @default.
- W2225956744 cites W1992969267 @default.
- W2225956744 cites W1997452076 @default.
- W2225956744 cites W2005218002 @default.
- W2225956744 cites W2017814585 @default.
- W2225956744 cites W2032293070 @default.
- W2225956744 cites W2064702271 @default.
- W2225956744 cites W2096150356 @default.
- W2225956744 cites W2098355199 @default.
- W2225956744 cites W2098594878 @default.
- W2225956744 cites W2110917409 @default.
- W2225956744 cites W2129201358 @default.
- W2225956744 cites W2132820324 @default.
- W2225956744 cites W2146352414 @default.
- W2225956744 cites W2151698683 @default.
- W2225956744 cites W2151992422 @default.
- W2225956744 cites W2151996626 @default.
- W2225956744 cites W2152571752 @default.
- W2225956744 cites W2153635508 @default.
- W2225956744 cites W2154880882 @default.
- W2225956744 cites W2155056756 @default.
- W2225956744 cites W2155871590 @default.
- W2225956744 cites W2161969291 @default.
- W2225956744 cites W2168356304 @default.
- W2225956744 cites W2183422957 @default.
- W2225956744 cites W2185342521 @default.
- W2225956744 cites W2294656809 @default.
- W2225956744 cites W2524400984 @default.
- W2225956744 cites W2534523274 @default.
- W2225956744 cites W2536208356 @default.
- W2225956744 cites W2951234442 @default.
- W2225956744 cites W2952446334 @default.
- W2225956744 cites W349800315 @default.
- W2225956744 hasPublicationYear "2015" @default.
- W2225956744 type Work @default.
- W2225956744 sameAs 2225956744 @default.
- W2225956744 citedByCount "2" @default.
- W2225956744 countsByYear W22259567442016 @default.
- W2225956744 countsByYear W22259567442018 @default.
- W2225956744 crossrefType "posted-content" @default.
- W2225956744 hasAuthorship W2225956744A5039389241 @default.
- W2225956744 hasAuthorship W2225956744A5044978076 @default.
- W2225956744 hasAuthorship W2225956744A5064961741 @default.
- W2225956744 hasAuthorship W2225956744A5084937810 @default.
- W2225956744 hasConcept C107673813 @default.
- W2225956744 hasConcept C124101348 @default.
- W2225956744 hasConcept C153083717 @default.
- W2225956744 hasConcept C153180895 @default.
- W2225956744 hasConcept C154945302 @default.
- W2225956744 hasConcept C166957645 @default.
- W2225956744 hasConcept C177769412 @default.
- W2225956744 hasConcept C205649164 @default.
- W2225956744 hasConcept C2779343474 @default.
- W2225956744 hasConcept C31972630 @default.
- W2225956744 hasConcept C41008148 @default.
- W2225956744 hasConcept C46686674 @default.
- W2225956744 hasConcept C64754055 @default.
- W2225956744 hasConcept C89600930 @default.
- W2225956744 hasConceptScore W2225956744C107673813 @default.
- W2225956744 hasConceptScore W2225956744C124101348 @default.
- W2225956744 hasConceptScore W2225956744C153083717 @default.
- W2225956744 hasConceptScore W2225956744C153180895 @default.
- W2225956744 hasConceptScore W2225956744C154945302 @default.
- W2225956744 hasConceptScore W2225956744C166957645 @default.
- W2225956744 hasConceptScore W2225956744C177769412 @default.
- W2225956744 hasConceptScore W2225956744C205649164 @default.
- W2225956744 hasConceptScore W2225956744C2779343474 @default.
- W2225956744 hasConceptScore W2225956744C31972630 @default.
- W2225956744 hasConceptScore W2225956744C41008148 @default.
- W2225956744 hasConceptScore W2225956744C46686674 @default.
- W2225956744 hasConceptScore W2225956744C64754055 @default.
- W2225956744 hasConceptScore W2225956744C89600930 @default.
- W2225956744 hasLocation W22259567441 @default.
- W2225956744 hasOpenAccess W2225956744 @default.
- W2225956744 hasPrimaryLocation W22259567441 @default.
- W2225956744 hasRelatedWork W1910817791 @default.
- W2225956744 hasRelatedWork W1990444762 @default.
- W2225956744 hasRelatedWork W2039125691 @default.
- W2225956744 hasRelatedWork W2101297579 @default.
- W2225956744 hasRelatedWork W2107228164 @default.
- W2225956744 hasRelatedWork W2572697301 @default.
- W2225956744 hasRelatedWork W2594062783 @default.