arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1701.00669cs.CV
收藏

乘积流形滤波器:基于乘积空间核密度估计的非刚性形状对应

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

Technical University Munich(慕尼黑工业大学);Tel-Aviv University(特拉维夫大学);USI Lugano(卢加诺大学);Technion, Israel Institute of Technology(以色列理工学院);Intel(英特尔)

Matthias Vestner, Roee Litman, Emanuele Rodolà, Alex Bronstein, Daniel Cremers

摘要:

用于计算可变形形状之间的对应关系的许多算法依赖于描述符空间中的最近邻匹配的某种变体。例如,这些是用作功能对应框架中的后处理阶段的各种逐点对应恢复算法。这种经常使用的技术隐含地做出限制性假设(例如,近似等距),并且在实践中缺乏准确性并导致差的满射性。我们提出了一种替代恢复技术,能够保证双射对应,并产生显着更高的准确性和平滑度。与其他方法不同,我们的方法不依赖于假设分析的形状是等距的。我们从核密度估计的统计框架中推导出所提出的方法,并在几个具有挑战性的可变形3D形状匹配数据集上证明了其性能。

英文摘要:

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 post-processing stage in the functional correspondence framework. Such frequently used techniques implicitly make restrictive assumptions (e.g., near-isometry) on the considered shapes and in practice suffer from lack of accuracy and result in poor surjectivity. We propose an alternative recovery technique capable of guaranteeing a bijective correspondence and producing significantly higher accuracy and smoothness. Unlike other methods our approach does not depend on the assumption that the analyzed shapes are isometric. We derive the proposed method from the statistical framework of kernel density estimation and demonstrate its performance on several challenging deformable 3D shape matching datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑