FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034879369> ?p ?o ?g. }

• W3034879369 abstract "Understanding the shape of a scene from a single color image is a formidable computer vision task. However, most methods aim to predict the geometry of surfaces that are visible to the camera, which is of limited use when planning paths for robots or augmented reality agents. Such agents can only move when grounded on a traversable surface, which we define as the set of classes which humans can also walk over, such as grass, footpaths and pavement. Models which predict beyond the line of sight often parameterize the scene with voxels or meshes, which can be expensive to use in machine learning frameworks. We introduce a model to predict the geometry of both visible and occluded traversable surfaces, given a single RGB image as input. We learn from stereo video sequences, using camera poses, per-frame depth and semantic segmentation to form training data, which is used to supervise an image-to-image network. We train models from the KITTI driving dataset, the indoor Matterport dataset, and from our own casually captured stereo footage. We find that a surprisingly low bar for spatial coverage of training scenes is required. We validate our algorithm against a range of strong baselines, and include an assessment of our predictions for a path-planning task." @default.
• W3034879369 created "2020-06-19" @default.
• W3034879369 creator A5016840801 @default.
• W3034879369 creator A5028022598 @default.
• W3034879369 creator A5038405331 @default.
• W3034879369 creator A5052163949 @default.
• W3034879369 date "2020-06-01" @default.
• W3034879369 modified "2023-09-26" @default.
• W3034879369 title "Footprints and Free Space From a Single Color Image" @default.
• W3034879369 cites W1966931935 @default.
• W3034879369 cites W1969483458 @default.
• W3034879369 cites W1987266124 @default.
• W3034879369 cites W1987648924 @default.
• W3034879369 cites W1991717955 @default.
• W3034879369 cites W2004887586 @default.
• W3034879369 cites W2005175937 @default.
• W3034879369 cites W2018299767 @default.
• W3034879369 cites W2030358157 @default.
• W3034879369 cites W2032293070 @default.
• W3034879369 cites W2044233231 @default.
• W3034879369 cites W2061482346 @default.
• W3034879369 cites W2085261163 @default.
• W3034879369 cites W2099144379 @default.
• W3034879369 cites W2112070512 @default.
• W3034879369 cites W2113107168 @default.
• W3034879369 cites W2143220699 @default.
• W3034879369 cites W2150066425 @default.
• W3034879369 cites W2152571752 @default.
• W3034879369 cites W2229637417 @default.
• W3034879369 cites W2340897893 @default.
• W3034879369 cites W2444097022 @default.
• W3034879369 cites W2460280001 @default.
• W3034879369 cites W2464328412 @default.
• W3034879369 cites W2520707372 @default.
• W3034879369 cites W2523049145 @default.
• W3034879369 cites W2534523274 @default.
• W3034879369 cites W2557465155 @default.
• W3034879369 cites W2560544142 @default.
• W3034879369 cites W2561196672 @default.
• W3034879369 cites W2593841437 @default.
• W3034879369 cites W2598108580 @default.
• W3034879369 cites W2609883120 @default.
• W3034879369 cites W2737258237 @default.
• W3034879369 cites W2883907768 @default.
• W3034879369 cites W2887848798 @default.
• W3034879369 cites W2942368658 @default.
• W3034879369 cites W2949023359 @default.
• W3034879369 cites W2953941229 @default.
• W3034879369 cites W2962807143 @default.
• W3034879369 cites W2962817776 @default.
• W3034879369 cites W2962864875 @default.
• W3034879369 cites W2963243172 @default.
• W3034879369 cites W2963488291 @default.
• W3034879369 cites W2963619659 @default.
• W3034879369 cites W2963660453 @default.
• W3034879369 cites W2963911235 @default.
• W3034879369 cites W2964156315 @default.
• W3034879369 cites W2964294967 @default.
• W3034879369 cites W2964325922 @default.
• W3034879369 cites W2970562905 @default.
• W3034879369 cites W2981518351 @default.
• W3034879369 cites W2985775862 @default.
• W3034879369 cites W2988715931 @default.
• W3034879369 cites W2990578762 @default.
• W3034879369 cites W3102327032 @default.
• W3034879369 cites W331766535 @default.
• W3034879369 doi "https://doi.org/10.1109/cvpr42600.2020.00009" @default.
• W3034879369 hasPublicationYear "2020" @default.
• W3034879369 type Work @default.
• W3034879369 sameAs 3034879369 @default.
• W3034879369 citedByCount "19" @default.
• W3034879369 countsByYear W30348793692020 @default.
• W3034879369 countsByYear W30348793692021 @default.
• W3034879369 countsByYear W30348793692022 @default.
• W3034879369 countsByYear W30348793692023 @default.
• W3034879369 crossrefType "proceedings-article" @default.
• W3034879369 hasAuthorship W3034879369A5016840801 @default.
• W3034879369 hasAuthorship W3034879369A5028022598 @default.
• W3034879369 hasAuthorship W3034879369A5038405331 @default.
• W3034879369 hasAuthorship W3034879369A5052163949 @default.
• W3034879369 hasBestOaLocation W30348793692 @default.
• W3034879369 hasConcept C115961682 @default.
• W3034879369 hasConcept C121684516 @default.
• W3034879369 hasConcept C154945302 @default.
• W3034879369 hasConcept C162324750 @default.
• W3034879369 hasConcept C177264268 @default.
• W3034879369 hasConcept C187736073 @default.
• W3034879369 hasConcept C199360897 @default.
• W3034879369 hasConcept C2780451532 @default.
• W3034879369 hasConcept C31487907 @default.
• W3034879369 hasConcept C31972630 @default.
• W3034879369 hasConcept C41008148 @default.
• W3034879369 hasConcept C54170458 @default.
• W3034879369 hasConcept C82990744 @default.
• W3034879369 hasConceptScore W3034879369C115961682 @default.
• W3034879369 hasConceptScore W3034879369C121684516 @default.
• W3034879369 hasConceptScore W3034879369C154945302 @default.
• W3034879369 hasConceptScore W3034879369C162324750 @default.
• W3034879369 hasConceptScore W3034879369C177264268 @default.
• W3034879369 hasConceptScore W3034879369C187736073 @default.

• next