Hierarchical part-type segmentation using voxel-based curve skeletons

D. Reniers, A.C. Telea

Research output: Contribution to journalArticleAcademicpeer-review

13 Citations (Scopus)

Abstract

We present an effective framework for segmenting 3D shapes into meaningful components using the curve skeleton. Our algorithm identifies a number of critical points on the efficiently computed curve skeleton, either fully automatically as the junctions of the curve skeleton, or based on user input. We use these points to construct a partitioning of the object surface using geodesics. Because the segmentation is based on the curve skeleton, it intrinsically reflects the shape symmetry and articulation, and can handle shapes with tunnels. We describe a voxel-based implementation of our method which is robust and noise resistant, able to handle shapes of complex articulation and topology, produces smooth segment borders, and delivers hierarchical level-of-detail segmentations. We demonstrate the framework on various real-world 3D shapes. Additionally, we discuss the use of both curve and surface skeletons to produce part-type and patch-type, respectively, segmentations of 3D shapes.
Original languageEnglish
Pages (from-to)383-395
JournalThe Visual Computer
Volume24
Issue number6
DOIs
Publication statusPublished - 2008

Fingerprint Dive into the research topics of 'Hierarchical part-type segmentation using voxel-based curve skeletons'. Together they form a unique fingerprint.

Cite this