A correspondence-less approach to matching of deformable shapes

Details A correspondence-less approach to matching of deformable shapes A correspondence-less approach to matching of deformable shapes

2011-01-29

arxiv.org/abs/1101.5687v1

Computer Science

Computer Vision and Pattern Recognition

Preprint submitted to Intl. Conference on Scale Space and Variational Methods (SSVM'11)

Scientific paper

Finding a match between partially available deformable shapes is a challenging problem with numerous applications. The problem is usually approached by computing local descriptors on a pair of shapes and then establishing a point-wise correspondence between the two. In this paper, we introduce an alternative correspondence-less approach to matching fragments to an entire shape undergoing a non-rigid deformation. We use diffusion geometric descriptors and optimize over the integration domains on which the integral descriptors of the two parts match. The problem is regularized using the Mumford-Shah functional. We show an efficient discretization based on the Ambrosio-Tortorelli approximation generalized to triangular meshes. Experiments demonstrating the success of the proposed method are presented.

Affiliated with

Also associated with

No associations

Rating

A correspondence-less approach to matching of deformable shapes does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A correspondence-less approach to matching of deformable shapes, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A correspondence-less approach to matching of deformable shapes will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-573449