Virtual Training for Multi-View Object Class Recognition

Our goal is to circumvent one of the roadblocks to using existing approaches for single-view recognition for achieving multi-view recognition, namely, the need for sufficient training data for many viewpoints. We show how to construct virtual training examples for multi-view recognition using a simple model of objects (nearly planar facades centered at fixed 3D positions). We also show how the models can be learned from a few labeled images for each class.

1. Introduction

Seeing a number of instances of an object class from different views ought to enable a vision system to recognize other instances of that class from views that have not been seen before. In most current approaches to object class recognition, the problem of recognizing multiple views of the same object class is treated as recognizing multiple independent object classes, with a separate model learned for each. This independent-view approach can be made to work well when there are many instances at different views available for training, but can typically only handle new viewpoints that are a small distance from some view on which it has been trained.