Interactive skeleton extraction for 3D animation using geodesic distances
ACM SIGGRAPH 2006 Research posters
Medial axis extraction and shape manipulation of solid objects using parabolic PDEs
SM '04 Proceedings of the ninth ACM symposium on Solid modeling and applications
Example-based skeleton extraction
SGP '07 Proceedings of the fifth Eurographics symposium on Geometry processing
Skeleton extraction by mesh contraction
ACM SIGGRAPH 2008 papers
Harmonic 1-form based skeleton extraction from examples
Graphical Models
Mathematical methods for shape analysis and form comparison in 3D anthropometry: a literature review
ICDHM'07 Proceedings of the 1st international conference on Digital human modeling
Automatic skeleton extraction and splitting of target objects
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
A mobile environment for sketching-based skeleton generation
World Wide Web
Image skeletonization based on curve skeleton extraction
HCII'11 Proceedings of the 14th international conference on Human-computer interaction: design and development approaches - Volume Part I
Curve skeleton extraction by graph contraction
CVM'12 Proceedings of the First international conference on Computational Visual Media
Combining topological and view-based features for 3D model retrieval
Multimedia Tools and Applications
Human action recognition based on skeleton splitting
Expert Systems with Applications: An International Journal
| Hi-index | 0.00 |
Skeleton is a lower dimensional shape description of anobject. The requirements of a skeleton differ with applications.For example, object recognition requires skele-tonswith primitive shape features to make similarity comparison.On the other hand, surface reconstruction needsskeletons which contain detailed geometry information toreduce the approximation error in the reconstruction process.Whereas many previous works are concerned aboutskeleton extraction, most of these methods are sensitive tonoise, time consuming, or restricted to specific 3D models.A practical approach for extracting skeletons from general3D models using radial basis functions (RBFs) is proposed.Skeleton generated with this approach conformsmore to the human perception. Given a 3D polygonalmodel, the vertices are regarded as centers for RBF level setconstruction. Next, a gradient descent algorithm is appliedto each vertex to locate the local maxima in the RBF; thegradient is calculated directly from the partial derivativesof the RBF. Finally, with the inherited connectivity from theoriginal model, local maximum pairs are connected withlinks driven by the active contour model. The skeletonizationprocess is completed when the potential energy of theselinks is minimized.