paper-with-me

홈 › Papers

Efficient Deformable Shape Correspondence via Kernel Matching

2017-07-25 · Zorah Lähner, Matthias Vestner, Amit Boyarski, Or Litany, Ron Slossberg, Tal Remez, Emanuele Rodolà, Alex Bronstein, Michael Bronstein, Ron Kimmel, Daniel Cremers

We present a method to match three dimensional shapes under non-isometric deformations, topology changes and partiality. We formulate the problem as matching between a set of pair-wise and point-wise descriptors, imposing a continuity prior on the mapping, and propose a projected descent optimization procedure inspired by difference of convex functions (DC) programming. Surprisingly, in spite of the highly non-convex nature of the resulting quadratic assignment problem, our method converges to a semantically meaningful and continuous mapping in most of our experiments, and scales well. We provide preliminary theoretical analysis and several interpretations of the method.

📄 PDF Abstract BibTeX arXiv:1707.08991

Code (1)

zorah/KernelMatching 공식 구현

Similar Papers 제목 키워드 기반

Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Space

2017-01-03 · CVPR 2017 7 · Matthias Vestner, Roee Litman, Emanuele Rodolà, Alex Bronstein 외

Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space. Such are, for example, various point-wise correspondence recovery …

Density Estimation

Bayesian Inference of Bijective Non-Rigid Shape Correspondence

2016-07-12 · Matthias Vestner, Roee Litman, Alex Bronstein, Emanuele Rodolà 외

Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space. Such are, for example, various point-wise correspondence recovery …

Bayesian Inference

MMGSD: Multi-Modal Gaussian Shape Descriptors for Correspondence Matching in 1D and 2D Deformable Objects

2020-10-09 · Aditya Ganapathi, Priya Sundaresan, Brijen Thananjeyan, Ashwin Balakrishna 외

We explore learning pixelwise correspondences between images of deformable objects in different configurations. Traditional correspondence matching approaches such as SIFT, SURF, and ORB can fail to provide sufficient co…

Contrastive Learning

Deformable Kernel Expansion Model for Efficient Arbitrary-shaped Scene Text Detection

2023-03-28 · Tao He, Sheng Huang, Wenhao Tang, Bo Liu

Scene text detection is a challenging computer vision task due to the high variation in text shapes and ratios. In this work, we propose a scene text detector named Deformable Kernel Expansion (DKE), which incorporates t…

Graph MatchingScene Text DetectionSegmentationText Detection

GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models

2023-04-20 · Haitao Yang, Xiangru Huang, Bo Sun, Chandrajit Bajaj 외

This paper introduces GenCorres, a novel unsupervised joint shape matching (JSM) approach. Our key idea is to learn a mesh generator to fit an unorganized deformable shape collection while constraining deformations betwe…