arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1601.00199cs.CV
收藏

主动外观模型的组合拟合统一框架

A Unified Framework for Compositional Fitting of Active Appearance Models

Imperial College London(帝国理工学院)

Joan Alabort-i-Medina, Stefanos Zafeiriou

摘要:

主动外观模型(AAM)是计算机视觉中用于建模可变形对象的最流行和成熟的技术之一。在本文中,我们研究的问题,拟合AAM的组合梯度下降(CGD)算法。我们提出了一个统一的和完整的视图,这些算法和分类的三个主要特征:i)成本函数; ii)类型的组合;和iii)优化方法。此外,我们扩展了以前的观点:a)提出了一种新的贝叶斯成本函数,可以被解释为一个通用的概率公式的著名的项目出损失; b)引入两种新的组合类型,不对称和双向,结合图像和外观模型的梯度,以获得更好的收敛和更强大的CGD算法;以及c)通过将现有的CGD算法重新解释为Schur补和Wiberg方法的直接应用,为现有的CGD算法提供新的有价值的见解。最后,为了鼓励开放式研究,并促进未来的比较与我们的工作,我们使本文研究的算法的实现公开提供的Menpo项目的一部分。

英文摘要:

Active Appearance Models (AAMs) are one of the most popular and well-established techniques for modeling deformable objects in computer vision. In this paper, we study the problem of fitting AAMs using Compositional Gradient Descent (CGD) algorithms. We present a unified and complete view of these algorithms and classify them with respect to three main characteristics: i) cost function; ii) type of composition; and iii) optimization method. Furthermore, we extend the previous view by: a) proposing a novel Bayesian cost function that can be interpreted as a general probabilistic formulation of the well-known project-out loss; b) introducing two new types of composition, asymmetric and bidirectional, that combine the gradients of both image and appearance model to derive better conver- gent and more robust CGD algorithms; and c) providing new valuable insights into existent CGD algorithms by reinterpreting them as direct applications of the Schur complement and the Wiberg method. Finally, in order to encourage open research and facilitate future comparisons with our work, we make the implementa- tion of the algorithms studied in this paper publicly available as part of the Menpo Project.

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。

↑