A 3-D reconstruction method based on epipolar geometry

This paper addresses the problem of 3-D reconstruction based on epipolar geometry, which uses the iterative linear subspace algorithm (ILSA). A high precise fundamental matrix can be computed by distance minimization starting from the position of epipolar points and epipolar transformation, which are estimated initially by the linear subspace algorithm. The algorithm has been implemented and tested on both synthetic and real images, and compared to other ones, the method is more robust and precise