This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
When you compute the homography using correspondences between two images, you are computing the real transformation between points if only if they all lie on the same plane or if the camera moved with perfect rotation. Otherwise the homography is just an approximation. The only way to map all the points in a pefect way is computing a dense 3D map between the two views using stereopsis.
