We describe a new direct method for estimating structure and motion from image intensities of multiple views. We extend the direct methods of Horn and Weldon  to three views. Adding the third view enables us to solve for motion and compute a dense depth map of the scene, directly from image spatio-temporal derivatives in a linear manner without first having to find point correspondence or compute optical flow. We describe the advantages and limitations of this method which are then verified with experiments using real images.
|Number of pages
|IEEE Transactions on Pattern Analysis and Machine Intelligence
|Published - Sep 2000
Bibliographical noteFunding Information:
The authors would like to acknowledge the US-IS BSF contract 94-00120 and the European ACTS project AC074. General support for Gideon P. Stein comes from DARPA contracts N00014-94-01-0994 and 95009-5381.