Suhit Gupta
08-10-2004, 06:00 PM
<div class='os_post_top_link'><a href='http://www.technologyreview.com/articles/04/08/rnb_080204.asp?trk=top' target='_blank'>http://www.technologyreview.com/articles/04/08/rnb_080204.asp?trk=top</a><br /><br /></div><i>"Researchers from the University of Washington and Microsoft Research have devised a method of automatically and seamlessly combining features of multiple photographs, including photographs that depict movement. The method, dubbed Interactive Digital Photomontage, automatically finds seams between parts of two or more source photographs after a user provides rough guidance. The software allow users to, for instance, make a composite photograph from several pictures of a group of people, according to the researchers."</i><br /><br />This will really help towards photo stitching software and would presumably make more people attempt project like the Gigapixel image. :) The method uses a graph-cut optimization technique to choose good seams and a gradient-domain fusion technique to smooth color differences along the seams. The system also allows users to make infinite depth-of-field images of microscopic subjects. Cool stuff, you can look forward to their paper at the upcoming ACM SIGGRAPH.