Reconstructing Open Surfaces from Image Data
International Journal of Computer Vision
Variational Surface Interpolation from Sparse Point and Normal Data
IEEE Transactions on Pattern Analysis and Machine Intelligence
Curvature minimization for surface reconstruction with features
SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision
| Hi-index | 0.00 |
In this paper the problem of building and reconstructing geometrical surface models from multiple calibrated images is considered. We build an appropriate statistical 3D model from the images alone and show how this a priori model can be used to automatically reconstruct new instances of the object category from one or several images. The surface reconstruction method is based on a level set representation and one of the main novel contributions lie within the level set framework. Standard methods use either image-correlation or point correspondences to achieve this goal. We show how this framework can be extended to incorporate image curves and apparent contours (i.e. the projections of silhouettes). In order to automatically obtain feature correspondences, we use a statistical shape modelfor the object category of interest. The model is based on the Active Shape Model using Probabilistic PCA. The scheme is applied to build and automatically reconstruct 3D surface models of faces. The resulting system is demonstrated on a database of real face images.