arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1607.03425cs.CV
收藏

双射非刚性形状对应的贝叶斯推断

Bayesian Inference of Bijective Non-Rigid Shape Correspondence

Technische Universität München(慕尼黑工业大学);Technion, Israel Institute of Technology(以色列理工学院);Intel(英特尔公司);Università della Svizzera italiana(瑞士意大利语区大学)

Matthias Vestner, Roee Litman, Alex Bronstein, Emanuele Rodolà, 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,这些是用作函数对应框架中的后处理阶段的各种逐点对应恢复算法。在本文中,我们表明,这种经常使用的技术在实践中遭受缺乏准确性,并导致不良的满射性。我们提出了一种替代恢复技术,保证双射对应并产生显着更高的准确性。我们从贝叶斯推理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形状匹配数据集上展示了其性能。

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 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.

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。

↑