arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0712.0136cs.CV
收藏

学习视图泛化功能

Learning View Generalization Functions

PARC(帕洛阿尔托研究中心)

Thomas M. Breuel

摘要:

在3D视觉目标识别中,从视图中学习目标模型通常被表述为描述目标的视图流形的函数的函数逼近问题,或者被表述为学习类条件密度的函数逼近问题。本文介绍了一种替代框架学习视觉对象识别,学习的观点,泛化功能。使用视图泛化功能,观察者可以直接在给定一个或多个2D训练视图的情况下执行贝叶斯最优3D对象识别,而不需要单独的模型获取步骤。本文表明,视图泛化功能可以计算实用重述两个广泛使用的方法,本征空间和线性组合的意见的方法,在一个视图泛化框架。本文涉及的方法,最近的目标识别方法的基础上非均匀模糊。本文介绍了结果模拟3D "回形针“的对象和现实世界的图像从COIL-100数据库显示,有用的视图泛化功能,可以现实地从一个相对较少的训练样本。

英文摘要:

Learning object models from views in 3D visual object recognition is usually formulated either as a function approximation problem of a function describing the view-manifold of an object, or as that of learning a class-conditional density. This paper describes an alternative framework for learning in visual object recognition, that of learning the view-generalization function. Using the view-generalization function, an observer can perform Bayes-optimal 3D object recognition given one or more 2D training views directly, without the need for a separate model acquisition step. The paper shows that view generalization functions can be computationally practical by restating two widely-used methods, the eigenspace and linear combination of views approaches, in a view generalization framework. The paper relates the approach to recent methods for object recognition based on non-uniform blurring. The paper presents results both on simulated 3D ``paperclip'' objects and real-world images from the COIL-100 database showing that useful view-generalization functions can be realistically be learned from a comparatively small number of training examples.

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。

↑