Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386076239> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4386076239 abstract "Vector graphics (VG) are ubiquitous in industrial designs. In this paper, we address semantic segmentation of a typical VG, i.e., roughcast floorplans with bare wall structures, whose output can be directly used for further applications like interior furnishing and room space modeling. Previous semantic segmentation works mostly process well-decorated floorplans in raster images and usually yield aliased boundaries and outlier fragments in segmented rooms, due to pixel-level segmentation that ignores the regular elements (e.g. line segments) in vector floor-plans. To overcome these issues, we propose to fully utilize the regular elements in vector floorplans for more integral segmentation. Our pipeline predicts room segmentation from vector floorplans by dually classifying line segments as room boundaries, and regions partitioned by line segments as room segments. To fully exploit the structural relationships between lines and regions, we use two-stream graph neural networks to process the line segments and partitioned regions respectively, and devise a novel modulated graph attention layer to fuse the heterogeneous information from one stream to the other. Extensive experiments show that by directly operating on vector floorplans, we outper-form image-based methods in both mIoU and mAcc. In addition, we propose a new metric that captures room integrity and boundary regularity, which confirms that our method produces much more regular segmentations. Source code is available at https://github.com/DrZiji/VecFloorSeg." @default.
- W4386076239 created "2023-08-23" @default.
- W4386076239 creator A5008794577 @default.
- W4386076239 creator A5043300312 @default.
- W4386076239 creator A5056602636 @default.
- W4386076239 creator A5076518693 @default.
- W4386076239 date "2023-06-01" @default.
- W4386076239 modified "2023-09-27" @default.
- W4386076239 title "VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation" @default.
- W4386076239 cites W1501856433 @default.
- W4386076239 cites W1832962863 @default.
- W4386076239 cites W1903029394 @default.
- W4386076239 cites W2014843742 @default.
- W4386076239 cites W2031118188 @default.
- W4386076239 cites W2141461755 @default.
- W4386076239 cites W2779637370 @default.
- W4386076239 cites W2912636151 @default.
- W4386076239 cites W2933283617 @default.
- W4386076239 cites W2963351448 @default.
- W4386076239 cites W2984769683 @default.
- W4386076239 cites W2986336497 @default.
- W4386076239 cites W2990045899 @default.
- W4386076239 cites W3042485697 @default.
- W4386076239 cites W3100848837 @default.
- W4386076239 cites W3138444776 @default.
- W4386076239 cites W3163206189 @default.
- W4386076239 cites W3173193115 @default.
- W4386076239 cites W3176366763 @default.
- W4386076239 cites W4286611064 @default.
- W4386076239 cites W4312266470 @default.
- W4386076239 doi "https://doi.org/10.1109/cvpr52729.2023.00137" @default.
- W4386076239 hasPublicationYear "2023" @default.
- W4386076239 type Work @default.
- W4386076239 citedByCount "0" @default.
- W4386076239 crossrefType "proceedings-article" @default.
- W4386076239 hasAuthorship W4386076239A5008794577 @default.
- W4386076239 hasAuthorship W4386076239A5043300312 @default.
- W4386076239 hasAuthorship W4386076239A5056602636 @default.
- W4386076239 hasAuthorship W4386076239A5076518693 @default.
- W4386076239 hasConcept C124504099 @default.
- W4386076239 hasConcept C130145326 @default.
- W4386076239 hasConcept C132525143 @default.
- W4386076239 hasConcept C149635348 @default.
- W4386076239 hasConcept C153180895 @default.
- W4386076239 hasConcept C154945302 @default.
- W4386076239 hasConcept C160633673 @default.
- W4386076239 hasConcept C181844469 @default.
- W4386076239 hasConcept C31972630 @default.
- W4386076239 hasConcept C41008148 @default.
- W4386076239 hasConcept C80444323 @default.
- W4386076239 hasConcept C89600930 @default.
- W4386076239 hasConceptScore W4386076239C124504099 @default.
- W4386076239 hasConceptScore W4386076239C130145326 @default.
- W4386076239 hasConceptScore W4386076239C132525143 @default.
- W4386076239 hasConceptScore W4386076239C149635348 @default.
- W4386076239 hasConceptScore W4386076239C153180895 @default.
- W4386076239 hasConceptScore W4386076239C154945302 @default.
- W4386076239 hasConceptScore W4386076239C160633673 @default.
- W4386076239 hasConceptScore W4386076239C181844469 @default.
- W4386076239 hasConceptScore W4386076239C31972630 @default.
- W4386076239 hasConceptScore W4386076239C41008148 @default.
- W4386076239 hasConceptScore W4386076239C80444323 @default.
- W4386076239 hasConceptScore W4386076239C89600930 @default.
- W4386076239 hasFunder F4320321001 @default.
- W4386076239 hasFunder F4320321543 @default.
- W4386076239 hasLocation W43860762391 @default.
- W4386076239 hasOpenAccess W4386076239 @default.
- W4386076239 hasPrimaryLocation W43860762391 @default.
- W4386076239 hasRelatedWork W121273120 @default.
- W4386076239 hasRelatedWork W1669643531 @default.
- W4386076239 hasRelatedWork W2005437358 @default.
- W4386076239 hasRelatedWork W2008656436 @default.
- W4386076239 hasRelatedWork W2023558673 @default.
- W4386076239 hasRelatedWork W2134924024 @default.
- W4386076239 hasRelatedWork W2337415362 @default.
- W4386076239 hasRelatedWork W2517104666 @default.
- W4386076239 hasRelatedWork W2740820121 @default.
- W4386076239 hasRelatedWork W4312857205 @default.
- W4386076239 isParatext "false" @default.
- W4386076239 isRetracted "false" @default.
- W4386076239 workType "article" @default.