Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204908658> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W3204908658 abstract "Volumetric design is the first and critical step for professional building design, where architects not only depict the rough 3D geometry of the building but also specify the programs to form a 2D layout on each floor. Though 2D layout generation for a single story has been widely studied, there is no developed method for multi-story buildings. This paper focuses on volumetric design generation conditioned on an input program graph. Instead of outputting dense 3D voxels, we propose a new 3D representation named voxel graph that is both compact and expressive for building geometries. Our generator is a cross-modal graph neural network that uses a pointer mechanism to connect the input program graph and the output voxel graph, and the whole pipeline is trained using the adversarial framework. The generated designs are evaluated qualitatively by a user study and quantitatively using three metrics: quality, diversity, and connectivity accuracy. We show that our model generates realistic 3D volumetric designs and outperforms previous methods and baselines." @default.
- W3204908658 created "2021-10-11" @default.
- W3204908658 creator A5007186141 @default.
- W3204908658 creator A5012706585 @default.
- W3204908658 creator A5024274481 @default.
- W3204908658 creator A5036275704 @default.
- W3204908658 creator A5070736865 @default.
- W3204908658 creator A5078025658 @default.
- W3204908658 date "2021-04-27" @default.
- W3204908658 modified "2023-10-14" @default.
- W3204908658 title "Building-GAN: Graph-Conditioned Architectural Volumetric Design Generation" @default.
- W3204908658 doi "https://doi.org/10.48550/arxiv.2104.13316" @default.
- W3204908658 hasPublicationYear "2021" @default.
- W3204908658 type Work @default.
- W3204908658 sameAs 3204908658 @default.
- W3204908658 citedByCount "0" @default.
- W3204908658 crossrefType "posted-content" @default.
- W3204908658 hasAuthorship W3204908658A5007186141 @default.
- W3204908658 hasAuthorship W3204908658A5012706585 @default.
- W3204908658 hasAuthorship W3204908658A5024274481 @default.
- W3204908658 hasAuthorship W3204908658A5036275704 @default.
- W3204908658 hasAuthorship W3204908658A5070736865 @default.
- W3204908658 hasAuthorship W3204908658A5078025658 @default.
- W3204908658 hasBestOaLocation W32049086581 @default.
- W3204908658 hasConcept C127413603 @default.
- W3204908658 hasConcept C132525143 @default.
- W3204908658 hasConcept C154945302 @default.
- W3204908658 hasConcept C179372163 @default.
- W3204908658 hasConcept C185592680 @default.
- W3204908658 hasConcept C188027245 @default.
- W3204908658 hasConcept C199639397 @default.
- W3204908658 hasConcept C205711294 @default.
- W3204908658 hasConcept C41008148 @default.
- W3204908658 hasConcept C54170458 @default.
- W3204908658 hasConcept C71139939 @default.
- W3204908658 hasConcept C80444323 @default.
- W3204908658 hasConceptScore W3204908658C127413603 @default.
- W3204908658 hasConceptScore W3204908658C132525143 @default.
- W3204908658 hasConceptScore W3204908658C154945302 @default.
- W3204908658 hasConceptScore W3204908658C179372163 @default.
- W3204908658 hasConceptScore W3204908658C185592680 @default.
- W3204908658 hasConceptScore W3204908658C188027245 @default.
- W3204908658 hasConceptScore W3204908658C199639397 @default.
- W3204908658 hasConceptScore W3204908658C205711294 @default.
- W3204908658 hasConceptScore W3204908658C41008148 @default.
- W3204908658 hasConceptScore W3204908658C54170458 @default.
- W3204908658 hasConceptScore W3204908658C71139939 @default.
- W3204908658 hasConceptScore W3204908658C80444323 @default.
- W3204908658 hasLocation W32049086581 @default.
- W3204908658 hasOpenAccess W3204908658 @default.
- W3204908658 hasPrimaryLocation W32049086581 @default.
- W3204908658 hasRelatedWork W2388332332 @default.
- W3204908658 hasRelatedWork W251114125 @default.
- W3204908658 hasRelatedWork W2761353030 @default.
- W3204908658 hasRelatedWork W2982299143 @default.
- W3204908658 hasRelatedWork W2995013067 @default.
- W3204908658 hasRelatedWork W3003634687 @default.
- W3204908658 hasRelatedWork W3094658021 @default.
- W3204908658 hasRelatedWork W3195541832 @default.
- W3204908658 hasRelatedWork W4320016041 @default.
- W3204908658 hasRelatedWork W802416172 @default.
- W3204908658 isParatext "false" @default.
- W3204908658 isRetracted "false" @default.
- W3204908658 magId "3204908658" @default.
- W3204908658 workType "article" @default.