Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963640720> ?p ?o ?g. }
- W2963640720 abstract "We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels. The key contribution of our method is its ability to handle large scenes with varying spatial extent, managing the cubic growth in data size as scene size increases. To this end, we devise a fully-convolutional generative 3D CNN model whose filter kernels are invariant to the overall scene size. The model can be trained on scene subvolumes but deployed on arbitrarily large scenes at test time. In addition, we propose a coarse-to-fine inference strategy in order to produce high-resolution output while also leveraging large input context sizes. In an extensive series of experiments, we carefully evaluate different model design choices, considering both deterministic and probabilistic models for completion and semantic inference. Our results show that we outperform other methods not only in the size of the environments handled and processing efficiency, but also with regard to completion quality and semantic segmentation performance by a significant margin." @default.
- W2963640720 created "2019-07-30" @default.
- W2963640720 creator A5005034184 @default.
- W2963640720 creator A5026634347 @default.
- W2963640720 creator A5058195612 @default.
- W2963640720 creator A5059110895 @default.
- W2963640720 creator A5083876835 @default.
- W2963640720 creator A5084377170 @default.
- W2963640720 date "2018-06-01" @default.
- W2963640720 modified "2023-09-30" @default.
- W2963640720 title "ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans" @default.
- W2963640720 cites W1625949922 @default.
- W2963640720 cites W1927784829 @default.
- W2963640720 cites W1953319329 @default.
- W2963640720 cites W1981349497 @default.
- W2963640720 cites W1987648924 @default.
- W2963640720 cites W1990345222 @default.
- W2963640720 cites W1992642990 @default.
- W2963640720 cites W2009422376 @default.
- W2963640720 cites W2014667763 @default.
- W2963640720 cites W2049351243 @default.
- W2963640720 cites W2052069724 @default.
- W2963640720 cites W2072202468 @default.
- W2963640720 cites W2097307110 @default.
- W2963640720 cites W2097374608 @default.
- W2963640720 cites W2099940712 @default.
- W2963640720 cites W2121669559 @default.
- W2963640720 cites W2187027887 @default.
- W2963640720 cites W2211722331 @default.
- W2963640720 cites W2250172176 @default.
- W2963640720 cites W2336961836 @default.
- W2963640720 cites W2427751284 @default.
- W2963640720 cites W2444097022 @default.
- W2963640720 cites W2556802233 @default.
- W2963640720 cites W2557465155 @default.
- W2963640720 cites W2559882727 @default.
- W2963640720 cites W2594519801 @default.
- W2963640720 cites W2962731536 @default.
- W2963640720 cites W2963648573 @default.
- W2963640720 cites W3104141662 @default.
- W2963640720 cites W4250463896 @default.
- W2963640720 cites W4297792443 @default.
- W2963640720 doi "https://doi.org/10.1109/cvpr.2018.00481" @default.
- W2963640720 hasPublicationYear "2018" @default.
- W2963640720 type Work @default.
- W2963640720 sameAs 2963640720 @default.
- W2963640720 citedByCount "221" @default.
- W2963640720 countsByYear W29636407202018 @default.
- W2963640720 countsByYear W29636407202019 @default.
- W2963640720 countsByYear W29636407202020 @default.
- W2963640720 countsByYear W29636407202021 @default.
- W2963640720 countsByYear W29636407202022 @default.
- W2963640720 countsByYear W29636407202023 @default.
- W2963640720 crossrefType "proceedings-article" @default.
- W2963640720 hasAuthorship W2963640720A5005034184 @default.
- W2963640720 hasAuthorship W2963640720A5026634347 @default.
- W2963640720 hasAuthorship W2963640720A5058195612 @default.
- W2963640720 hasAuthorship W2963640720A5059110895 @default.
- W2963640720 hasAuthorship W2963640720A5083876835 @default.
- W2963640720 hasAuthorship W2963640720A5084377170 @default.
- W2963640720 hasBestOaLocation W29636407202 @default.
- W2963640720 hasConcept C119857082 @default.
- W2963640720 hasConcept C151730666 @default.
- W2963640720 hasConcept C153180895 @default.
- W2963640720 hasConcept C154945302 @default.
- W2963640720 hasConcept C26517878 @default.
- W2963640720 hasConcept C2776214188 @default.
- W2963640720 hasConcept C2779343474 @default.
- W2963640720 hasConcept C31972630 @default.
- W2963640720 hasConcept C38652104 @default.
- W2963640720 hasConcept C41008148 @default.
- W2963640720 hasConcept C49937458 @default.
- W2963640720 hasConcept C774472 @default.
- W2963640720 hasConcept C86803240 @default.
- W2963640720 hasConcept C89600930 @default.
- W2963640720 hasConceptScore W2963640720C119857082 @default.
- W2963640720 hasConceptScore W2963640720C151730666 @default.
- W2963640720 hasConceptScore W2963640720C153180895 @default.
- W2963640720 hasConceptScore W2963640720C154945302 @default.
- W2963640720 hasConceptScore W2963640720C26517878 @default.
- W2963640720 hasConceptScore W2963640720C2776214188 @default.
- W2963640720 hasConceptScore W2963640720C2779343474 @default.
- W2963640720 hasConceptScore W2963640720C31972630 @default.
- W2963640720 hasConceptScore W2963640720C38652104 @default.
- W2963640720 hasConceptScore W2963640720C41008148 @default.
- W2963640720 hasConceptScore W2963640720C49937458 @default.
- W2963640720 hasConceptScore W2963640720C774472 @default.
- W2963640720 hasConceptScore W2963640720C86803240 @default.
- W2963640720 hasConceptScore W2963640720C89600930 @default.
- W2963640720 hasLocation W29636407201 @default.
- W2963640720 hasLocation W29636407202 @default.
- W2963640720 hasOpenAccess W2963640720 @default.
- W2963640720 hasPrimaryLocation W29636407201 @default.
- W2963640720 hasRelatedWork W1669643531 @default.
- W2963640720 hasRelatedWork W2005437358 @default.
- W2963640720 hasRelatedWork W2008656436 @default.
- W2963640720 hasRelatedWork W2023558673 @default.
- W2963640720 hasRelatedWork W2039154422 @default.
- W2963640720 hasRelatedWork W2122581818 @default.
- W2963640720 hasRelatedWork W2134924024 @default.