Matches in SemOpenAlex for { <https://semopenalex.org/work/W2794739174> ?p ?o ?g. }
- W2794739174 abstract "The goal of our work is to complete the depth channel of an RGB-D image. Commodity-grade depth cameras often fail to sense depth for shiny, bright, transparent, and distant surfaces. To address this problem, we train a deep network that takes an RGB image as input and predicts dense surface normals and occlusion boundaries. Those predictions are then combined with raw depth observations provided by the RGB-D camera to solve for depths for all pixels, including those missing in the original observation. This method was chosen over others (e.g., inpainting depths directly) as the result of extensive experiments with a new depth completion benchmark dataset, where holes are filled in training data through the rendering of surface reconstructions created from multiview RGB-D scans. Experiments with different network inputs, depth representations, loss functions, optimization methods, inpainting methods, and deep depth estimation networks show that our proposed approach provides better depth completions than these alternatives." @default.
- W2794739174 created "2018-04-06" @default.
- W2794739174 creator A5058136382 @default.
- W2794739174 creator A5079619886 @default.
- W2794739174 date "2018-06-01" @default.
- W2794739174 modified "2023-10-03" @default.
- W2794739174 title "Deep Depth Completion of a Single RGB-D Image" @default.
- W2794739174 cites W125693051 @default.
- W2794739174 cites W1803059841 @default.
- W2794739174 cites W1872406745 @default.
- W2794739174 cites W1897173520 @default.
- W2794739174 cites W1899309388 @default.
- W2794739174 cites W1905829557 @default.
- W2794739174 cites W1918878870 @default.
- W2794739174 cites W1923779427 @default.
- W2794739174 cites W1967027087 @default.
- W2794739174 cites W1981705310 @default.
- W2794739174 cites W1982840500 @default.
- W2794739174 cites W1985238052 @default.
- W2794739174 cites W1992642990 @default.
- W2794739174 cites W2001022596 @default.
- W2794739174 cites W2001140913 @default.
- W2794739174 cites W2005441409 @default.
- W2794739174 cites W2012788443 @default.
- W2794739174 cites W2021191215 @default.
- W2794739174 cites W2026672030 @default.
- W2794739174 cites W2028401795 @default.
- W2794739174 cites W2030978325 @default.
- W2794739174 cites W2031181766 @default.
- W2794739174 cites W2097074225 @default.
- W2794739174 cites W2101872283 @default.
- W2794739174 cites W2104620097 @default.
- W2794739174 cites W2110892967 @default.
- W2794739174 cites W2116567847 @default.
- W2794739174 cites W2117751343 @default.
- W2794739174 cites W2118304946 @default.
- W2794739174 cites W2130067871 @default.
- W2794739174 cites W2132750878 @default.
- W2794739174 cites W2132947399 @default.
- W2794739174 cites W2151996626 @default.
- W2794739174 cites W2153388956 @default.
- W2794739174 cites W2165736859 @default.
- W2794739174 cites W2404752729 @default.
- W2794739174 cites W2431126524 @default.
- W2794739174 cites W2436453945 @default.
- W2794739174 cites W2563100679 @default.
- W2794739174 cites W2563685048 @default.
- W2794739174 cites W2594519801 @default.
- W2794739174 cites W2734032203 @default.
- W2794739174 cites W2766955733 @default.
- W2794739174 cites W2776330782 @default.
- W2794739174 cites W2780175898 @default.
- W2794739174 cites W2962807621 @default.
- W2794739174 cites W2962809185 @default.
- W2794739174 cites W2963316641 @default.
- W2794739174 cites W2963420272 @default.
- W2794739174 cites W2963591054 @default.
- W2794739174 cites W2963939259 @default.
- W2794739174 cites W2964339842 @default.
- W2794739174 cites W3101501663 @default.
- W2794739174 cites W53941081 @default.
- W2794739174 doi "https://doi.org/10.1109/cvpr.2018.00026" @default.
- W2794739174 hasPublicationYear "2018" @default.
- W2794739174 type Work @default.
- W2794739174 sameAs 2794739174 @default.
- W2794739174 citedByCount "263" @default.
- W2794739174 countsByYear W27947391742018 @default.
- W2794739174 countsByYear W27947391742019 @default.
- W2794739174 countsByYear W27947391742020 @default.
- W2794739174 countsByYear W27947391742021 @default.
- W2794739174 countsByYear W27947391742022 @default.
- W2794739174 countsByYear W27947391742023 @default.
- W2794739174 crossrefType "proceedings-article" @default.
- W2794739174 hasAuthorship W2794739174A5058136382 @default.
- W2794739174 hasAuthorship W2794739174A5079619886 @default.
- W2794739174 hasBestOaLocation W27947391742 @default.
- W2794739174 hasConcept C108583219 @default.
- W2794739174 hasConcept C115961682 @default.
- W2794739174 hasConcept C11727466 @default.
- W2794739174 hasConcept C121684516 @default.
- W2794739174 hasConcept C127162648 @default.
- W2794739174 hasConcept C127313418 @default.
- W2794739174 hasConcept C13280743 @default.
- W2794739174 hasConcept C141268832 @default.
- W2794739174 hasConcept C154945302 @default.
- W2794739174 hasConcept C160633673 @default.
- W2794739174 hasConcept C185798385 @default.
- W2794739174 hasConcept C200873422 @default.
- W2794739174 hasConcept C205711294 @default.
- W2794739174 hasConcept C31258907 @default.
- W2794739174 hasConcept C31972630 @default.
- W2794739174 hasConcept C41008148 @default.
- W2794739174 hasConcept C82990744 @default.
- W2794739174 hasConceptScore W2794739174C108583219 @default.
- W2794739174 hasConceptScore W2794739174C115961682 @default.
- W2794739174 hasConceptScore W2794739174C11727466 @default.
- W2794739174 hasConceptScore W2794739174C121684516 @default.
- W2794739174 hasConceptScore W2794739174C127162648 @default.
- W2794739174 hasConceptScore W2794739174C127313418 @default.
- W2794739174 hasConceptScore W2794739174C13280743 @default.