This paper presents an approach to the problem of intra-operative reconstruction of 3D anatomical surfaces. The method is based on the integration of intra-operatively available shape and image data of different dimensionality such as 3D scattered point data, 2.5D ultra sound data, X-ray images etc. by matching them to a statistical shape model, thus providing the surgeon with a complete surface representation of the object of interest. Previous papers of the authors describe the matching of either 3D or 2D data to a statistical model and clinical applications. The here presented work combines former published ideas with a new approach for the complex task of shape analysis required for the computation of the statistical model, thus providing a generic approach for intra-operative surface reconstruction based on statistical models. The method for shape extraction/analysis is based on a generic model of the object and is used to segment training shapes and to establish point to point correspondence simultaneously in a set of CT images. Reconstruction experiments are performed on a statistical model of lumbar vertebrae. Results are provided for 3D/3D, 2D/3D and hybrid matching with simulated data and for 3D/2D matching for a cadaveric spine.