Computational schemes for biomimetic sculpture
Proceedings of the 5th conference on Creativity & cognition
Rapid prototyping 3D objects from scanned measurement data
Image and Vision Computing
Onboard contextual classification of 3-D point clouds with learned high-order Markov random fields
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Surface reconstruction from stereo data using three-dimensional markov random field model
ICAPR'05 Proceedings of the Third international conference on Pattern Recognition and Image Analysis - Volume Part II
Markov random fields for improving 3D mesh analysis and segmentation
EG 3DOR'08 Proceedings of the 1st Eurographics conference on 3D Object Retrieval
Hi-index | 0.01 |
This paper introduces a new stochastic surface model for deformable 3D surfaces and demonstrates its utility for the purpose of 3D sculpting. This is the problem of simple-to-use and intuitively interactive 3D free-form model building. A 3D surface is a sample of a Markov Random Field (MRF) defined on the vertices of a 3D mesh where MRF sites coincide with mesh vertices and the MRF cliques consist of subsets of sites. Each site has 3D coordinates (x,y,z) as random variables and is a member of one or more clique potentials which are functions of the vertices in a clique and describe stochastic dependencies among sites. Data, which is used to deform the surface can consist of, but is not limited to, an unorganized set of 3D points and is modeled by a conditional probability distribution given the 3D surface. A deformed surface is a MAP (Maximum A posteriori Probability) estimate of the joint distribution of the MRF surface model and the data. The generality and simplicity of the MRF model provides the ability to incorporate unlimited local and global deformation properties. Included in our development is the introduction of new data models, new anisotropic clique potentials, and cliques which involve sites that are spatially far apart. Other applications of these models are possible, e.g., stereo reconstruction.