|
Published Articles >> Table of Contents >> Abstract
Fourth International Conference on 3-D Digital Imaging and Modeling (3DIM '03)
p. 147
A Range Image Refinement Technique for Multi-view 3D Model Reconstruction
Soon-Yong Park, State University of New York at Stony Brook, USA
Murali Subbarao, State University of New York at Stony Brook, USA
Full Article Text:
 
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/IM.2003.1240244
Send link to a friend
| Abstract |
|
This paper presents a range image refinement technique
for generating accurate 3D computer models of real objects.
Range images obtained from a stereo-vision system
typically experience geometric distortions on reconstructed
3D surfaces due to the inherent stereo matching problems
such as occlusions or mismatchings. This paper introduces
a range image refinement technique to correct such erroneous
ranges by employing epipolar geometry of a multi-view
modeling system and the visual hull of an object. After
registering multiple range images into a common coordinate
system, we first determine if a 3D point in a range image
is erroneous, by measuring registration of the point with
its correspondences in other range images. The correspondences
are determined on 3D contours which are inverse-projections
of epipolar lines in other 2D silhouette images.
Then the range of the point is refined onto the object's surface,
if it is erroneous. We employ two techniques to search
the correspondences fast. In case that there is no correspondence
for an erroneous point, we refine the point onto
the visual hull of the object. We show that refined range images
yield better geometric structures in reconstructed 3D
models.
|
 Additional Information
|
Citation:
Soon-Yong Park, Murali Subbarao,
"A Range Image Refinement Technique for Multi-view 3D Model Reconstruction,"
3dim,
p. 147,
Fourth International Conference on 3-D Digital Imaging and Modeling (3DIM '03),
2003
|
|
