A Method for Registration of 3-D Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Partition regularity of (M, P, C)-systems
Journal of Combinatorial Theory Series A
Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
The space of human body shapes: reconstruction and parameterization from range scans
ACM SIGGRAPH 2003 Papers
Deformation transfer for triangle meshes
ACM SIGGRAPH 2004 Papers
Fast and robust detection of crest lines on meshes
Proceedings of the 2005 ACM symposium on Solid and physical modeling
Linear rotation-invariant coordinates for meshes
ACM SIGGRAPH 2005 Papers
Global non-rigid alignment of 3-D scans
ACM SIGGRAPH 2007 papers
Example-based skeleton extraction
SGP '07 Proceedings of the fifth Eurographics symposium on Geometry processing
ACM Transactions on Graphics (TOG)
Skeleton extraction by mesh contraction
ACM SIGGRAPH 2008 papers
Feature Correspondence Via Graph Matching: Models and Global Optimization
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
ACM SIGGRAPH 2009 papers
Robust single-view geometry and motion reconstruction
ACM SIGGRAPH Asia 2009 papers
A deformation transformer for real-time cloth animation
ACM SIGGRAPH 2010 papers
Hi-index | 0.00 |
Consistence of topology for 3D models with such rich details as pores and wrinkles is very important for performing higher level tasks like deformation and animation. In this paper, we propose a novel wrinkle-aware registration method, which aligns not only the large-scale poses, but also high-resolution deformable details, in a unified framework. Using large-scale alignment enables us to solve a template-based energy minimization problem through pure Euclidean measurement. Fine-scale features are aligned by firstly computing crest lines for both the intermediately registered mesh and the target, and then evaluating the shape descriptors at the feature points, followed by a graph matching procedure to achieve a global optimization of the closest point matching. Experiments show that our method is effective and robust in preserving the quality of the source, while matching the fine-scale details of the target.