Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313176528> ?p ?o ?g. }
- W4313176528 endingPage "654" @default.
- W4313176528 startingPage "637" @default.
- W4313176528 abstract "Significant geometric structures can be compactly described by global wireframes in the estimation of 3D room layout from a single panoramic image. Based on this observation, we present an alternative approach to estimate the walls in 3D space by modeling long-range geometric patterns in a learnable Hough Transform block. We transform the image feature from a cubemap tile to the Hough space of a Manhattan world and directly map the feature to the geometric output. The convolutional layers not only learn the local gradient-like line features, but also utilize the global information to successfully predict occluded walls with a simple network structure. Unlike most previous work, the predictions are performed individually on each cubemap tile, and then assembled to get the layout estimation. Experimental results show that we achieve comparable results with recent state-of-the-art in prediction accuracy and performance. Code is available at https://github.com/Starrah/DMH-Net ." @default.
- W4313176528 created "2023-01-06" @default.
- W4313176528 creator A5001543788 @default.
- W4313176528 creator A5019740622 @default.
- W4313176528 creator A5048412206 @default.
- W4313176528 creator A5060470295 @default.
- W4313176528 date "2022-01-01" @default.
- W4313176528 modified "2023-10-02" @default.
- W4313176528 title "3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform" @default.
- W4313176528 cites W1481823314 @default.
- W4313176528 cites W1965834447 @default.
- W4313176528 cites W1971866894 @default.
- W4313176528 cites W2068397385 @default.
- W4313176528 cites W2091276368 @default.
- W4313176528 cites W2102271310 @default.
- W4313176528 cites W2115728367 @default.
- W4313176528 cites W2116851763 @default.
- W4313176528 cites W2145023731 @default.
- W4313176528 cites W2156802865 @default.
- W4313176528 cites W2194775991 @default.
- W4313176528 cites W2199215860 @default.
- W4313176528 cites W2264103933 @default.
- W4313176528 cites W22745672 @default.
- W4313176528 cites W2425789671 @default.
- W4313176528 cites W2439650069 @default.
- W4313176528 cites W2534523274 @default.
- W4313176528 cites W2598108580 @default.
- W4313176528 cites W2799029219 @default.
- W4313176528 cites W2902957614 @default.
- W4313176528 cites W2962717701 @default.
- W4313176528 cites W2962850830 @default.
- W4313176528 cites W2963433827 @default.
- W4313176528 cites W2963591013 @default.
- W4313176528 cites W2964030239 @default.
- W4313176528 cites W2964180491 @default.
- W4313176528 cites W2964339842 @default.
- W4313176528 cites W2988715931 @default.
- W4313176528 cites W2999254410 @default.
- W4313176528 cites W3013329510 @default.
- W4313176528 cites W3047878062 @default.
- W4313176528 cites W3092407498 @default.
- W4313176528 cites W3107016113 @default.
- W4313176528 cites W3126899967 @default.
- W4313176528 cites W3155772318 @default.
- W4313176528 cites W3158491882 @default.
- W4313176528 cites W3175201472 @default.
- W4313176528 cites W3186500138 @default.
- W4313176528 cites W4250952223 @default.
- W4313176528 cites W4312866948 @default.
- W4313176528 cites W566730006 @default.
- W4313176528 doi "https://doi.org/10.1007/978-3-031-19769-7_37" @default.
- W4313176528 hasPublicationYear "2022" @default.
- W4313176528 type Work @default.
- W4313176528 citedByCount "3" @default.
- W4313176528 countsByYear W43131765282023 @default.
- W4313176528 crossrefType "book-chapter" @default.
- W4313176528 hasAuthorship W4313176528A5001543788 @default.
- W4313176528 hasAuthorship W4313176528A5019740622 @default.
- W4313176528 hasAuthorship W4313176528A5048412206 @default.
- W4313176528 hasAuthorship W4313176528A5060470295 @default.
- W4313176528 hasBestOaLocation W43131765282 @default.
- W4313176528 hasConcept C115961682 @default.
- W4313176528 hasConcept C121684516 @default.
- W4313176528 hasConcept C138885662 @default.
- W4313176528 hasConcept C153180895 @default.
- W4313176528 hasConcept C154945302 @default.
- W4313176528 hasConcept C166957645 @default.
- W4313176528 hasConcept C198352243 @default.
- W4313176528 hasConcept C200518788 @default.
- W4313176528 hasConcept C205649164 @default.
- W4313176528 hasConcept C2524010 @default.
- W4313176528 hasConcept C2776401178 @default.
- W4313176528 hasConcept C2777210771 @default.
- W4313176528 hasConcept C2780580889 @default.
- W4313176528 hasConcept C2780728851 @default.
- W4313176528 hasConcept C31972630 @default.
- W4313176528 hasConcept C33923547 @default.
- W4313176528 hasConcept C41008148 @default.
- W4313176528 hasConcept C41895202 @default.
- W4313176528 hasConceptScore W4313176528C115961682 @default.
- W4313176528 hasConceptScore W4313176528C121684516 @default.
- W4313176528 hasConceptScore W4313176528C138885662 @default.
- W4313176528 hasConceptScore W4313176528C153180895 @default.
- W4313176528 hasConceptScore W4313176528C154945302 @default.
- W4313176528 hasConceptScore W4313176528C166957645 @default.
- W4313176528 hasConceptScore W4313176528C198352243 @default.
- W4313176528 hasConceptScore W4313176528C200518788 @default.
- W4313176528 hasConceptScore W4313176528C205649164 @default.
- W4313176528 hasConceptScore W4313176528C2524010 @default.
- W4313176528 hasConceptScore W4313176528C2776401178 @default.
- W4313176528 hasConceptScore W4313176528C2777210771 @default.
- W4313176528 hasConceptScore W4313176528C2780580889 @default.
- W4313176528 hasConceptScore W4313176528C2780728851 @default.
- W4313176528 hasConceptScore W4313176528C31972630 @default.
- W4313176528 hasConceptScore W4313176528C33923547 @default.
- W4313176528 hasConceptScore W4313176528C41008148 @default.
- W4313176528 hasConceptScore W4313176528C41895202 @default.
- W4313176528 hasLocation W43131765281 @default.