Abstract
This paper presents several novel techniques in the proposed semi-automatic system for reconstructing three-dimensional models of Jadeite material from uncalibrated image sequences. There are two major challenges for this 3D model reconstruction problem. The first is the difficult image registration problem due to the semi-diaphaneity and the highly specular property of Jadeite materials. Secondly, the unknown camera information, including the intrinsic (calibration) and extrinsic (position and orientation) parameters, to be recovered from the uncalibrated image sequences makes the robust 3D reconstruction problem very challenging. The proposed 3D modeling process first recovers the camera information as well as rough 3D structure by using a robust structure from motion algorithm, and then further extracts the fine details of the model from dense correspondences between image patches of different views. We have developed three new robust techniques for this challenging task, including a robust structure from motion algorithm, a robust image registration algorithm, and a robust dense depth computation algorithm. Finally, experimental results of the three-dimensional model reconstruction from the image sequence of the Chinese treasure, Jadeite Cabbage with Insects, are given to demonstrate the performance of the developed system. © 2005 SPIE and IS&T.