Depth-layer Architecture Reconstruction From Image Collections

Simple item page
dc.contributor.authorYong Huen_US
dc.contributor.authorBei Chuen_US
dc.contributor.authorYue Qien_US
dc.contributor.editorThomas Funkhouser and Shi-Min Huen_US
dc.date.accessioned2015-06-05T07:06:43Z
dc.date.available2015-06-05T07:06:43Z
dc.date.issued2014en_US
dc.description.abstractAn image-based modeling method is presented to generate a textured 3D model of architecture with a structure of multiple floors and depth layers. In the domain of image-based architecture modeling, it is still a challenging problem to deal with architecture in multilayered structure. We propose a statistic-based top-bottom segmentation algorithm to divide the 3D point cloud generated by structure-from-motion (SFM) method into different floors. For each floor with depth layers, we present a repetition based depth-layer decomposition algorithm to separate the front and back layers. Finally, architecture components are modeled to construct a textured 3D model. Our system has the distinct advantage of producing realistic architecture models with true depth values between front and back layers, which is demonstrated by multiple examples in the paper.en_US
dc.description.seriesinformationSymposium on Geometry Processing 2014 - Postersen_US
dc.identifier.isbn-en_US
dc.identifier.issn-en_US
dc.identifier.urihttps://doi.org/10.2312/sgp20141382en_US
dc.publisherThe Eurographics Associationen_US
dc.titleDepth-layer Architecture Reconstruction From Image Collectionsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
poster1048.pdf
Size:
8.14 MB
Format:
Adobe Portable Document Format
Download
Collections
SGP14: Eurographics Symposium on Geometry Processing - Posters