The estimation of dense 3D point clouds from image sequences
is discussed by Pollefeys et al. [Pollefeys et al.
2000] and Brown et al. [Brown et al. 2003]. The geometrical
theory of these methods relies on being able to solve
the reconstruction problem. From corresponding points
the relative orientation can be estimated and 3D points
are extracted. These procedure is applied to many pixels
within stereo or multiview images which results in dense
3D point clouds.