Non-rigid 3D object retrieval using topological information guided by conformal factors

Sfikas, Konstantinos; Theoharis, Theoharis; Pratikakis, Ioannis

doi:10.1007/s00371-012-0714-z

Cited by 32 publications

(18 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to these geometric descriptors, topological representations are also very popular for shape retrieval and understanding [17]. They include mostly graph representations like Reeb graphs [18][19][20] or simpler region adjacency graphs obtained from a segmentation [21].…”

Section: Shape Descriptionmentioning

confidence: 99%

Continuous semantic description of 3D meshes

León

Bonneel

Lavoué

et al. 2016

Computers & Graphics

View full text Add to dashboard Cite

International audienceWe propose a novel high-level signature for continuous semantic description of 3D shapes. Given an approximately segmented and labeled 3D mesh, our descriptor consists of a set of geodesic distances to the different semantic labels. This local multidimensional signature effectively captures both the semantic information (and relationships between labels) and the underlying geometry and topology of the shape. We illustrate its benefits on two applications: automatic semantic labeling, seen as an inverse problem along with supervised-learning, and semantic-aware shape editing for which the isocurves of our harmonic description are particularly relevant

show abstract

Section: Shape Descriptionmentioning

confidence: 99%

Continuous semantic description of 3D meshes

León

Bonneel

Lavoué

et al. 2016

Computers & Graphics

View full text Add to dashboard Cite

show abstract

“…The histogram of conformal factors [21] serves as a robust poseinvariant signature of 3D shape, which is regarded as an attribute of a graph node to identify segmented parts in bipartite graph matching for 3D shape retrieval [22]. In a recent work [23], 3D shape is also partitioned into several connected iso-surfaces (annuluses) of conformal factors, and expressed with a graph where node substitutes each annulus.…”

Section: Related Workmentioning

confidence: 99%

Local deep feature learning framework for 3D shape

Han

Liu

et al. 2015

Computers & Graphics

View full text Add to dashboard Cite

“…Sfikas et al [23] produce a graph representation using geometry-based discrete conformal factors [5].…”

Section: Related Workmentioning

confidence: 99%

Euclidean-distance-based canonical forms for non-rigid 3D shape retrieval

Pickup

Sun

Rosin

et al. 2015

Pattern Recognition

View full text Add to dashboard Cite

Retrieval of 3D shapes is a challenging problem, especially for non-rigid shapes.One approach giving favourable results uses multidimensional scaling (MDS) to compute a canonical form for each mesh, after which rigid shape matching can be applied. However, a drawback of this method is that it requires geodesic distances to be computed between all pairs of mesh vertices. Due to the superquadratic computational complexity, canonical forms can only be computed for low-resolution meshes. We suggest a linear time complexity method for computing a canonical form, using Euclidean distances between pairs of a small subset of vertices. This approach has comparable retrieval accuracy but lower time complexity than using global geodesic distances, allowing it to be used on higher resolution meshes, or for more meshes to be considered within a time budget.

show abstract

Non-rigid 3D object retrieval using topological information guided by conformal factors

Cited by 32 publications

References 36 publications

Continuous semantic description of 3D meshes

Continuous semantic description of 3D meshes

Local deep feature learning framework for 3D shape

Euclidean-distance-based canonical forms for non-rigid 3D shape retrieval

Contact Info

Product

Resources

About