An iterative method for reconstructing a 3D polygonal mesh and color texture map from multiple views of an object is presented. In each iteration, the method first estimates a texture map given the current shape estimate. The texture map and its associated residual error image are obtained via maximum a posteriori estimation and reprojection of the multiple views into texture space. Next, the surface shape is adjusted to minimize residual error in texture space. The surface is deformed towards a photometrically-consistent solution via a series of 1D epipolar searches at randomly selected surface points. The texture space formulation has improved computational complexity over standard image-based error approaches, and allows computation of the reprojection error and uncertainty for any point on the surface. Moreover, shape adjustments can be constrained such that the recovered model's silhouette matches those of the input images. Experiments with real world imagery demonstrate the validity of the approach.
Stochastic refinement of the visual hull to satisfy photometric and silhouette consistency constraints
Proceedings Ninth IEEE International Conference on Computer Vision ; 1335-1342 vol.2
2003-01-01
1138919 byte
Conference paper
Electronic Resource
English
British Library Conference Proceedings | 2003
|British Library Conference Proceedings | 2003
|Learning pedestrian models for silhouette refinement
IEEE | 2003
|Learning Pedestrian Models for Silhouette Refinement
British Library Conference Proceedings | 2003
|