Flexible 3D models from uncalibrated cameras

T. F. Cootes, E. C. Di Mauro, C. J. Taylor, A. Lanitis

    Research output: Contribution to journalArticlepeer-review


    We describe how to build statistically-based flexible models of the 3D structure of variable objects, given a training set of uncalibrated images. We assume that for each example object there are two labelled images taken from different viewpoints. From each image pair a 3D structure can be reconstructed, up to either an affine or projective transformation, depending on which camera model is used. The reconstructions are aligned by choosing the transformations which minimise the distances between matched points across the training set. A statistical analysis results in an estimate of the mean structure of the training examples and a compact parameterised model of the variability in shape across the training set. Experiments have been performed using pinhole and affine camera models. Results are presented for both synthetic data and real images.
    Original languageEnglish
    Pages (from-to)581-587
    Number of pages6
    JournalImage and Vision Computing
    Issue number8
    Publication statusPublished - Aug 1996


    • Learning in computer vision
    • Projective geometry
    • Shape and object representation
    • Uncalibrated cameras


    Dive into the research topics of 'Flexible 3D models from uncalibrated cameras'. Together they form a unique fingerprint.

    Cite this