Euclidean constraints for uncalibrated reconstruction

It is possible to recouer the three-dimensional structure of a scene using images taken with ancalibrated cameras and pixel correspondences between these images. But such reconstruction can only be performed up to a projective transformation of the SD space. Therefore constraints have t o be put on the reconstructed data in order t o gel the reconstruction in the euclidean space. Such constraints arise from knowledge of the scene: location of points, geometrical constraints on lines, etc. W e discuss here the kind of constraints that have to be added and show how they can be fed in a general fmmework. Experimental results on real data prove the feasability, and experiments on simulated data address the accuracy of the results.