A novel approach for computing partial similarity between 3d models

Authors:
Wei Chen
Affiliations:
State Key Lab of CAD&CG, Zhejiang University
Venue:
FSKD'06 Proceedings of the Third international conference on Fuzzy Systems and Knowledge Discovery
Year:
2006

Citing 5
Cited 0

Least-Squares Estimation of Transformation Parameters Between Two Point Patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape distributions

ACM Transactions on Graphics (TOG)
Estimating the tensor of curvature of a surface from a polyhedral approximation

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Finding Color and Shape Patterns in Images

Finding Color and Shape Patterns in Images
Modeling by example

ACM SIGGRAPH 2004 Papers

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present our initial solution to partial similarity computation between arbitrary 3D polygon models. The task is considered as the estimation of similarity transformations between the query pattern and target object. Two steps accounting for the scaling and rotation/translation parts are carried out, facilitated by applying EMD (earth mover's distance) to search the correspondence between focused point sets. In order to reduce the computation complexity involved in the second step, we use K-means algorithm to cluster the vertices of each model. We report our early experiments testing the efficiency of the proposed method on a small database as well as detailed discussions and the outline for the future work.