Joint Feature Distributions for Image Correspondence

We introduce `Joint Feature Distributions', a general statistical framework for feature based multi-image matching that explicitly models the joint probability distributions of corresponding features across several images. Conditioning on feature positions in some of the images gives well-localized distributions for their correspondents in the others, and hence tight likelihood regions for correspondence search. We apply the framework in the simplest case of Gaussian-like distributions over the direct sum (affine images) and tensor product (projective images) of the image coordinates. This produces probabilistic correspondence models that generalize the geometric multi-image matching constraints, roughly speaking by a form of model-averaging over them. These very simple methods predict accurate correspondence likelihood regions for any scene geometry including planar and near-planar scenes, without illconditioning or explicit model selection. Small amounts of distortion and non-r...

• Type: Conference
• Year: 2001
• Where: ICCV
• Authors: Bill Triggs
• Keywords: Computer Vision, Correspondence Likelihood Regions, ICCV 2001, Joint Feature Distributions, Joint Probability Distributions, Multi-image Matching Constraints, Tight Likelihood Regions