Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384207919> ?p ?o ?g. }
- W4384207919 endingPage "262" @default.
- W4384207919 startingPage "254" @default.
- W4384207919 abstract "Traditional urban reconstruction methods can only output incomplete 3D models, which depict the scene regions that are visible to the moving camera. While learning-based shape reconstruction techniques make single-view 3D reconstruction possible, they are designed to handle single objects that are well-presented in the training datasets. This paper presents a novel learning-based approach for reconstructing complete 3D meshes for large-scale urban scenes in real-time. The input video sequences are fed into a localization module, which segments different objects and determines their relative positions. Each object is then reconstructed under their local coordinates to better approximate models in the training datasets. The reconstruction module is adopted from BSP-Net Chen et al. (2020), which is capable of producing compact polygon meshes. However, major changes have been made so that unoriented objects in large-scale scenes can be reconstructed efficiently using only a small number of planes. Experimental results demonstrate that our approach can reconstruct urban scenes with buildings and vehicles using 400 ∼ 800 convex parts in 0.1 ∼ 0.5 s." @default.
- W4384207919 created "2023-07-14" @default.
- W4384207919 creator A5034304352 @default.
- W4384207919 creator A5050811619 @default.
- W4384207919 creator A5067516009 @default.
- W4384207919 creator A5089815515 @default.
- W4384207919 creator A5091227928 @default.
- W4384207919 date "2023-10-01" @default.
- W4384207919 modified "2023-09-25" @default.
- W4384207919 title "PA-Net: Plane attention network for real-time urban scene reconstruction" @default.
- W4384207919 cites W1803059841 @default.
- W4384207919 cites W1905829557 @default.
- W4384207919 cites W1970504153 @default.
- W4384207919 cites W2044655699 @default.
- W4384207919 cites W2113243634 @default.
- W4384207919 cites W2118304946 @default.
- W4384207919 cites W2152671441 @default.
- W4384207919 cites W2300779272 @default.
- W4384207919 cites W2474281075 @default.
- W4384207919 cites W2520707372 @default.
- W4384207919 cites W2557465155 @default.
- W4384207919 cites W2603429625 @default.
- W4384207919 cites W2806070179 @default.
- W4384207919 cites W2890382763 @default.
- W4384207919 cites W2905288042 @default.
- W4384207919 cites W2956121407 @default.
- W4384207919 cites W2962831196 @default.
- W4384207919 cites W2963583471 @default.
- W4384207919 cites W2963627347 @default.
- W4384207919 cites W2963926543 @default.
- W4384207919 cites W2990946490 @default.
- W4384207919 cites W3033193681 @default.
- W4384207919 cites W3034700465 @default.
- W4384207919 cites W3034848995 @default.
- W4384207919 cites W3035163517 @default.
- W4384207919 cites W3035269921 @default.
- W4384207919 cites W3035292206 @default.
- W4384207919 cites W3035424742 @default.
- W4384207919 cites W3089979672 @default.
- W4384207919 cites W3090386798 @default.
- W4384207919 cites W3098467253 @default.
- W4384207919 cites W3099472416 @default.
- W4384207919 cites W3102327032 @default.
- W4384207919 cites W3123674811 @default.
- W4384207919 cites W3127066163 @default.
- W4384207919 cites W3160589050 @default.
- W4384207919 cites W3172610252 @default.
- W4384207919 cites W3174960126 @default.
- W4384207919 cites W4200074884 @default.
- W4384207919 cites W4225371802 @default.
- W4384207919 cites W4225986494 @default.
- W4384207919 cites W4233857083 @default.
- W4384207919 cites W4288809167 @default.
- W4384207919 cites W4312398233 @default.
- W4384207919 cites W4312842946 @default.
- W4384207919 cites W4312878643 @default.
- W4384207919 cites W612478963 @default.
- W4384207919 doi "https://doi.org/10.1016/j.cag.2023.07.023" @default.
- W4384207919 hasPublicationYear "2023" @default.
- W4384207919 type Work @default.
- W4384207919 citedByCount "0" @default.
- W4384207919 crossrefType "journal-article" @default.
- W4384207919 hasAuthorship W4384207919A5034304352 @default.
- W4384207919 hasAuthorship W4384207919A5050811619 @default.
- W4384207919 hasAuthorship W4384207919A5067516009 @default.
- W4384207919 hasAuthorship W4384207919A5089815515 @default.
- W4384207919 hasAuthorship W4384207919A5091227928 @default.
- W4384207919 hasConcept C109950114 @default.
- W4384207919 hasConcept C112680207 @default.
- W4384207919 hasConcept C121684516 @default.
- W4384207919 hasConcept C126042441 @default.
- W4384207919 hasConcept C14166107 @default.
- W4384207919 hasConcept C154945302 @default.
- W4384207919 hasConcept C17825722 @default.
- W4384207919 hasConcept C190694206 @default.
- W4384207919 hasConcept C205649164 @default.
- W4384207919 hasConcept C2524010 @default.
- W4384207919 hasConcept C2778755073 @default.
- W4384207919 hasConcept C2781238097 @default.
- W4384207919 hasConcept C31487907 @default.
- W4384207919 hasConcept C31972630 @default.
- W4384207919 hasConcept C33923547 @default.
- W4384207919 hasConcept C41008148 @default.
- W4384207919 hasConcept C58640448 @default.
- W4384207919 hasConcept C76155785 @default.
- W4384207919 hasConceptScore W4384207919C109950114 @default.
- W4384207919 hasConceptScore W4384207919C112680207 @default.
- W4384207919 hasConceptScore W4384207919C121684516 @default.
- W4384207919 hasConceptScore W4384207919C126042441 @default.
- W4384207919 hasConceptScore W4384207919C14166107 @default.
- W4384207919 hasConceptScore W4384207919C154945302 @default.
- W4384207919 hasConceptScore W4384207919C17825722 @default.
- W4384207919 hasConceptScore W4384207919C190694206 @default.
- W4384207919 hasConceptScore W4384207919C205649164 @default.
- W4384207919 hasConceptScore W4384207919C2524010 @default.
- W4384207919 hasConceptScore W4384207919C2778755073 @default.
- W4384207919 hasConceptScore W4384207919C2781238097 @default.
- W4384207919 hasConceptScore W4384207919C31487907 @default.