Title
Data fusion for photorealistic 3d models
Abstract
This study aims at building photorealistic 3D models of real-world objects. We discuss the problem of combining a 3D textureless model obtained by 3D scanner, with optical images that provide textural information of the object. Recently, we have proposed a novel method to register an uncalibrated image pair to a 3D surface model. After registration, the images are mapped to the surface. However, as the images show different parts of the objects, partial overlapping textures can only be extracted from them. Combining the images into a complete texture map that covers the entire object is not trivial. We present a method to build photorealistic 3D models that includes algorithms for data registration and for merging multiple texture maps using surface flattening. Experimental results on real and synthetic data are shown.
Year
DOI
Venue
2005
10.1007/11556121_30
CAIP
Keywords
Field
DocType
surface model,novel method,data fusion,partial overlapping texture,multiple texture map,entire object,data registration,real-world object,complete texture map,synthetic data,surface flattening,optical imaging,texture mapping
Texture mapping,Computer vision,Flattening,Pattern recognition,Computer science,Image texture,Image processing,Sensor fusion,Synthetic data,Scanner,Artificial intelligence,Image registration
Conference
Volume
ISSN
ISBN
3691
0302-9743
3-540-28969-0
Citations 
PageRank 
References 
0
0.34
17
Authors
2
Name
Order
Citations
PageRank
Zsolt Jankó1335.94
Chetverikov, D.295699.89