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 ill-conditioning or explicit model selection. Small amounts of distortion and non-rigidity are also tolerated. We develop the theory for any number of affine or projective images, explain its relationship to matching tensors, and give results for an initial implementation.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Joint feature distributions for image correspondence


    Contributors:
    Triggs, B. (author)


    Publication date :

    2001-01-01


    Size :

    954420 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Joint Feature Distributions for Image Correspondence

    Triggs, B. / IEEE | British Library Conference Proceedings | 2001


    Global image feature correspondence under a multi-image network

    Shao, J. | British Library Online Contents | 1999



    Entropy-of-likelihood Feature Selection for Image Correspondence

    Toews, M. / Arbel, T. / IEEE | British Library Conference Proceedings | 2003


    Joint Inference in Weakly-Annotated Image Datasets via Dense Correspondence

    Rubinstein, M. / Liu, C. / Freeman, W. T. | British Library Online Contents | 2016