Paper Info
Title
Image Guided Geometry Inference
Abstract
We introduce a new method for filling holes in geometry obtained from 3D range scanners. Our method makes use of 2D images of the areas where geometric data is missing. The 2D images guide the filling using the relationship between the images and geometry learned from the existing 3D scanned data. Our method builds on existing techniques for using scanned geometry and for estimating shape from shaded images. Rather than creating plausibly filled holes, we attempt to approximate the missing geometry. We present results for scanned data from both triangulation and time-of-flight scanners for various types of materials. To quantitatively validate our proposed method, we also compare the filled areas with ground-truth data.
Year
DOI
Venue
2006
10.1109/3DPVT.2006.81
3DPVT
Keywords
Field
DocType
shaded image,image processing,range scanner,triangulation,3d range scanners,geometry inference,computational geometry,present result,scanned geometry,time-of-flight scanners,shape estimation,ground-truth data,geometric data,image-guided geometry inference,scanned data,missing geometry,new method,cultural differences,ground truth,computer vision,solid modeling,computer science,shape from shading,digital images,shape,computed tomography,time measurement
Geometric data analysis,Computer vision,Computer graphics (images),Inference,Computational geometry,Image processing,Triangulation (social science),Artificial intelligence,Geometry,Mathematics
Conference
ISBN
Citations 
PageRank 
0-7695-2825-2
7
0.46
References 
Authors
17
5
Name
Order
Citations
PageRank
Songhua Xu138023.09
Athinodoros S. Georghiades22483128.27
Holly Rushmeier32294334.25
Julie Dorsey42535182.80
Leonard McMillan53685323.97