paper-with-me

Papers

Bayesian Inference of Bijective Non-Rigid Shape Correspondence

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

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 algorithms used as a postprocessing stage in the functional correspondence framework. In this paper, we show that such frequently used techniques in practice suffer from lack of accuracy and result in poor surjectivity. We propose an alternative recovery technique guaranteeing a bijective correspondence and producing significantly higher accuracy. We derive the proposed method from a statistical framework of Bayesian inference and demonstrate its performance on several challenging deformable 3D shape matching datasets.

📄 PDF Abstract BibTeX arXiv:1607.03425

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian Inference

Similar Papers 제목 키워드 기반

Fast Sinkhorn Filters: Using Matrix Scaling for Non-Rigid Shape Correspondence With Functional Maps

2021-06-19 · CVPR 2021 1 · Gautam Pai, Jing Ren, Simone Melzi, Peter Wonka 외

In this paper, we provide a theoretical foundation for pointwise map recovery from functional maps and highlight its relation to a range of shape correspondence methods based on spectral alignment. With this analysis…

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

Matching Shapes Under Different Topologies: A Topology-Adaptive Deformation Guided Approach

2025-09-08 · Aymen Merrouche, Stefanie Wuhrer, Edmond Boyer arxiv

Non-rigid 3D mesh matching is a critical step in computer vision and computer graphics pipelines. We tackle matching meshes that contain topological artefacts which can break the assumption made by current approaches. Wh…

Mapping in a cycle: Sinkhorn regularized unsupervised learning for point cloud shapes

2020-07-19 · ECCV 2020 8 · Lei Yang, Wenxi Liu, Zhiming Cui, Nenglun Chen 외

We propose an unsupervised learning framework with the pretext task of finding dense correspondences between point cloud shapes from the same category based on the cycle-consistency formulation. In order to learn discrim…

Triplet

On Nonrigid Shape Similarity and Correspondence

2013-11-18 · Alon Shtern, Ron Kimmel

An important operation in geometry processing is finding the correspondences between pairs of shapes. The Gromov-Hausdorff distance, a measure of dissimilarity between metric spaces, has been found to be highly useful fo…