Transductive 3D Shape Segmentation using Sparse Reconstruction

Simple item page
dc.contributor.authorXu, Weiweien_US
dc.contributor.authorShi, Zhouxuen_US
dc.contributor.authorXu, Mingliangen_US
dc.contributor.authorZhou, Kunen_US
dc.contributor.authorWang, Jingdongen_US
dc.contributor.authorZhou, Binen_US
dc.contributor.authorWang, Jinrongen_US
dc.contributor.authorYuan, Zhenmingen_US
dc.contributor.editorThomas Funkhouser and Shi-Min Huen_US
dc.date.accessioned2015-03-03T12:41:46Z
dc.date.available2015-03-03T12:41:46Z
dc.date.issued2014en_US
dc.description.abstractWe propose a transductive shape segmentation algorithm, which can transfer prior segmentation results in database to new shapes without explicitly specification of prior category information. Our method first partitions an input shape into a set of segmentations as a data preparation, and then a linear integer programming algorithm is used to select segments from them to form the final optimal segmentation. The key idea is to maximize the segment similarity between the segments in the input shape and the segments in database, where the segment similarity is computed through sparse reconstruction error. The segment-level similarity enables to handle a large amount of shapes with significant topology or shape variations with a small set of segmented example shapes. Experimental results show that our algorithm can generate high quality segmentation and semantic labeling results in the Princeton segmentation benchmark.en_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.identifier.doi10.1111/cgf.12436en_US
dc.identifier.issn1467-8659en_US
dc.identifier.urihttps://doi.org/10.1111/cgf.12436en_US
dc.publisherThe Eurographics Association and John Wiley and Sons Ltd.en_US
dc.titleTransductive 3D Shape Segmentation using Sparse Reconstructionen_US
Files
Collections
33-Issue 5
SGP14: Eurographics Symposium on Geometry Processing (CGF 33-5)