Matches in SemOpenAlex for { <https://semopenalex.org/work/W2908617908> ?p ?o ?g. }
- W2908617908 abstract "We present a new approach to the problem of estimating the 3D room layout from a single panoramic image. We represent room layout as three 1D vectors that encode, at each image column, the boundary positions of floor-wall and ceiling-wall, and the existence of wall-wall boundary. The proposed network, HorizonNet, trained for predicting 1D layout, outperforms previous state-of-the-art approaches. The designed post-processing procedure for recovering 3D room layouts from 1D predictions can automatically infer the room shape with low computation cost - it takes less than 20ms for a panorama image while prior works might need dozens of seconds. We also propose Pano Stretch Data Augmentation, which can diversify panorama data and be applied to other panorama-related learning tasks. Due to the limited data available for non-cuboid layout, we relabel 65 general layout from the current dataset for finetuning. Our approach shows good performance on general layouts by qualitative results and cross-validation." @default.
- W2908617908 created "2019-01-25" @default.
- W2908617908 creator A5006394450 @default.
- W2908617908 creator A5037179146 @default.
- W2908617908 creator A5049121809 @default.
- W2908617908 creator A5089070900 @default.
- W2908617908 date "2019-01-12" @default.
- W2908617908 modified "2023-09-28" @default.
- W2908617908 title "HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation" @default.
- W2908617908 cites W1481823314 @default.
- W2908617908 cites W1901129140 @default.
- W2908617908 cites W1965834447 @default.
- W2908617908 cites W1969778848 @default.
- W2908617908 cites W2064675550 @default.
- W2908617908 cites W2068397385 @default.
- W2908617908 cites W2102271310 @default.
- W2908617908 cites W2109443835 @default.
- W2908617908 cites W2116851763 @default.
- W2908617908 cites W2125310925 @default.
- W2908617908 cites W2131774270 @default.
- W2908617908 cites W2145567954 @default.
- W2908617908 cites W2156802865 @default.
- W2908617908 cites W2168439642 @default.
- W2908617908 cites W2194775991 @default.
- W2908617908 cites W2199215860 @default.
- W2908617908 cites W2425789671 @default.
- W2908617908 cites W2439650069 @default.
- W2908617908 cites W2534523274 @default.
- W2908617908 cites W2560023338 @default.
- W2908617908 cites W2586114507 @default.
- W2908617908 cites W2598108580 @default.
- W2908617908 cites W2794800539 @default.
- W2908617908 cites W2799029219 @default.
- W2908617908 cites W2808817531 @default.
- W2908617908 cites W2888842498 @default.
- W2908617908 cites W2899771611 @default.
- W2908617908 cites W2921730933 @default.
- W2908617908 cites W2953678868 @default.
- W2908617908 cites W2963591013 @default.
- W2908617908 cites W2964030239 @default.
- W2908617908 cites W2964121744 @default.
- W2908617908 cites W2964180491 @default.
- W2908617908 cites W566730006 @default.
- W2908617908 doi "https://doi.org/10.48550/arxiv.1901.03861" @default.
- W2908617908 hasPublicationYear "2019" @default.
- W2908617908 type Work @default.
- W2908617908 sameAs 2908617908 @default.
- W2908617908 citedByCount "6" @default.
- W2908617908 countsByYear W29086179082019 @default.
- W2908617908 countsByYear W29086179082020 @default.
- W2908617908 countsByYear W29086179082021 @default.
- W2908617908 crossrefType "posted-content" @default.
- W2908617908 hasAuthorship W2908617908A5006394450 @default.
- W2908617908 hasAuthorship W2908617908A5037179146 @default.
- W2908617908 hasAuthorship W2908617908A5049121809 @default.
- W2908617908 hasAuthorship W2908617908A5089070900 @default.
- W2908617908 hasBestOaLocation W29086179081 @default.
- W2908617908 hasConcept C104317684 @default.
- W2908617908 hasConcept C11413529 @default.
- W2908617908 hasConcept C115961682 @default.
- W2908617908 hasConcept C121684516 @default.
- W2908617908 hasConcept C13280743 @default.
- W2908617908 hasConcept C134306372 @default.
- W2908617908 hasConcept C154945302 @default.
- W2908617908 hasConcept C176809094 @default.
- W2908617908 hasConcept C17744445 @default.
- W2908617908 hasConcept C185592680 @default.
- W2908617908 hasConcept C199539241 @default.
- W2908617908 hasConcept C205649164 @default.
- W2908617908 hasConcept C2776359362 @default.
- W2908617908 hasConcept C2780580889 @default.
- W2908617908 hasConcept C31972630 @default.
- W2908617908 hasConcept C33923547 @default.
- W2908617908 hasConcept C41008148 @default.
- W2908617908 hasConcept C45374587 @default.
- W2908617908 hasConcept C55493867 @default.
- W2908617908 hasConcept C62354387 @default.
- W2908617908 hasConcept C66746571 @default.
- W2908617908 hasConcept C94625758 @default.
- W2908617908 hasConceptScore W2908617908C104317684 @default.
- W2908617908 hasConceptScore W2908617908C11413529 @default.
- W2908617908 hasConceptScore W2908617908C115961682 @default.
- W2908617908 hasConceptScore W2908617908C121684516 @default.
- W2908617908 hasConceptScore W2908617908C13280743 @default.
- W2908617908 hasConceptScore W2908617908C134306372 @default.
- W2908617908 hasConceptScore W2908617908C154945302 @default.
- W2908617908 hasConceptScore W2908617908C176809094 @default.
- W2908617908 hasConceptScore W2908617908C17744445 @default.
- W2908617908 hasConceptScore W2908617908C185592680 @default.
- W2908617908 hasConceptScore W2908617908C199539241 @default.
- W2908617908 hasConceptScore W2908617908C205649164 @default.
- W2908617908 hasConceptScore W2908617908C2776359362 @default.
- W2908617908 hasConceptScore W2908617908C2780580889 @default.
- W2908617908 hasConceptScore W2908617908C31972630 @default.
- W2908617908 hasConceptScore W2908617908C33923547 @default.
- W2908617908 hasConceptScore W2908617908C41008148 @default.
- W2908617908 hasConceptScore W2908617908C45374587 @default.
- W2908617908 hasConceptScore W2908617908C55493867 @default.
- W2908617908 hasConceptScore W2908617908C62354387 @default.
- W2908617908 hasConceptScore W2908617908C66746571 @default.