Matches in SemOpenAlex for { <https://semopenalex.org/work/W2798314605> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2798314605 abstract "3D shape completion from partial point clouds is a fundamental problem in computer vision and computer graphics. Recent approaches can be characterized as either data-driven or learning-based. Data-driven approaches rely on a shape model whose parameters are optimized to fit the observations. Learning-based approaches, in contrast, avoid the expensive optimization step and instead directly predict the complete shape from the incomplete observations using deep neural networks. However, full supervision is required which is often not available in practice. In this work, we propose a weakly-supervised learning-based approach to 3D shape completion which neither requires slow optimization nor direct supervision. While we also learn a shape prior on synthetic data, we amortize, i.e., learn, maximum likelihood fitting using deep neural networks resulting in efficient shape completion without sacrificing accuracy. Tackling 3D shape completion of cars on ShapeNet [5] and KITTI [18], we demonstrate that the proposed amortized maximum likelihood approach is able to compete with a fully supervised baseline and a state-of-the-art data-driven approach while being significantly faster. On ModelNet [49], we additionally show that the approach is able to generalize to other object categories as well." @default.
- W2798314605 created "2018-05-07" @default.
- W2798314605 creator A5002157796 @default.
- W2798314605 creator A5016606943 @default.
- W2798314605 date "2018-06-01" @default.
- W2798314605 modified "2023-10-03" @default.
- W2798314605 title "Learning 3D Shape Completion from Laser Scan Data with Weak Supervision" @default.
- W2798314605 cites W1552539182 @default.
- W2798314605 cites W1905829557 @default.
- W2798314605 cites W1921093919 @default.
- W2798314605 cites W1932937519 @default.
- W2798314605 cites W1949568868 @default.
- W2798314605 cites W1953319329 @default.
- W2798314605 cites W1995050439 @default.
- W2798314605 cites W2014667763 @default.
- W2798314605 cites W2019040424 @default.
- W2798314605 cites W2083624211 @default.
- W2798314605 cites W2085905957 @default.
- W2798314605 cites W2097307110 @default.
- W2798314605 cites W2119493293 @default.
- W2798314605 cites W2143255850 @default.
- W2798314605 cites W2150066425 @default.
- W2798314605 cites W2444097022 @default.
- W2798314605 cites W2559882727 @default.
- W2798314605 cites W2603429625 @default.
- W2798314605 cites W2963591054 @default.
- W2798314605 cites W2963648573 @default.
- W2798314605 cites W2964162504 @default.
- W2798314605 cites W3106025793 @default.
- W2798314605 cites W4206760982 @default.
- W2798314605 cites W4297792443 @default.
- W2798314605 doi "https://doi.org/10.1109/cvpr.2018.00209" @default.
- W2798314605 hasPublicationYear "2018" @default.
- W2798314605 type Work @default.
- W2798314605 sameAs 2798314605 @default.
- W2798314605 citedByCount "175" @default.
- W2798314605 countsByYear W27983146052018 @default.
- W2798314605 countsByYear W27983146052019 @default.
- W2798314605 countsByYear W27983146052020 @default.
- W2798314605 countsByYear W27983146052021 @default.
- W2798314605 countsByYear W27983146052022 @default.
- W2798314605 countsByYear W27983146052023 @default.
- W2798314605 crossrefType "proceedings-article" @default.
- W2798314605 hasAuthorship W2798314605A5002157796 @default.
- W2798314605 hasAuthorship W2798314605A5016606943 @default.
- W2798314605 hasConcept C127413603 @default.
- W2798314605 hasConcept C154945302 @default.
- W2798314605 hasConcept C2779538338 @default.
- W2798314605 hasConcept C31972630 @default.
- W2798314605 hasConcept C41008148 @default.
- W2798314605 hasConcept C78519656 @default.
- W2798314605 hasConceptScore W2798314605C127413603 @default.
- W2798314605 hasConceptScore W2798314605C154945302 @default.
- W2798314605 hasConceptScore W2798314605C2779538338 @default.
- W2798314605 hasConceptScore W2798314605C31972630 @default.
- W2798314605 hasConceptScore W2798314605C41008148 @default.
- W2798314605 hasConceptScore W2798314605C78519656 @default.
- W2798314605 hasLocation W27983146051 @default.
- W2798314605 hasOpenAccess W2798314605 @default.
- W2798314605 hasPrimaryLocation W27983146051 @default.
- W2798314605 hasRelatedWork W1891287906 @default.
- W2798314605 hasRelatedWork W1969923398 @default.
- W2798314605 hasRelatedWork W2036807459 @default.
- W2798314605 hasRelatedWork W2058170566 @default.
- W2798314605 hasRelatedWork W2170022336 @default.
- W2798314605 hasRelatedWork W2229312674 @default.
- W2798314605 hasRelatedWork W258625772 @default.
- W2798314605 hasRelatedWork W2755342338 @default.
- W2798314605 hasRelatedWork W2772917594 @default.
- W2798314605 hasRelatedWork W3116076068 @default.
- W2798314605 isParatext "false" @default.
- W2798314605 isRetracted "false" @default.
- W2798314605 magId "2798314605" @default.
- W2798314605 workType "article" @default.