Learning View Generalization Functions

dc.creatorBreuel, Thomas M.
dc.date2007-12-02
dc.date.accessioned2026-07-07T08:46:46Z
dc.date.available2026-07-07T08:46:46Z
dc.descriptionLearning 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.
dc.identifierhttps://arxiv.org/abs/0712.0136
dc.identifierhttp://arxiv.org/abs/0712.0136
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/143365
dc.subjectComputer Vision and Pattern Recognition
dc.subjectI.4.8; I.2.10
dc.titleLearning View Generalization Functions
dc.typetext

Files

Collections