DocumentCode :
2206991
Title :
Efficient reconstruction of indoor scenes with color
Author :
Wang, Rui ; Luebke, David
Author_Institution :
Dept. of Comput. Sci., Virginia Univ., Charlottesville, VA, USA
fYear :
2003
fDate :
6-10 Oct. 2003
Firstpage :
402
Lastpage :
409
Abstract :
We present an efficient and general approach to computing and integrating 3D distance fields directly from multiple range images. We compute normal and confidence values directly from a 2D range image. We then approximate 3D Euclidean distance by correcting the line-of-sight distance. To integrate multiple scans, we efficiently transform voxels of the target distance field to each scan´s local coordinate system, then update voxels with computed distance and confidence values. Finally, we extract an iso-surface from the weighted distance field using the marching cubes algorithm. We extend the same idea to the assignment of weighted colors or texture coordinates to the reconstructed model. Experiments show that our approach is fast, has reasonable storage requirements, and can produce high-quality surfaces from multiple range scans.
Keywords :
computational geometry; feature extraction; image colour analysis; image reconstruction; image registration; image resolution; image scanners; image texture; natural scenes; solid modelling; 2D range image; 3D Euclidean distance approximation; 3D distance field computation; 3D distance field integration; confidence value; indoor scene reconstruction; line-of-sight distance; marching cubes algorithm; multiple range scan; scan local coordinate system; texture coordinates; weighted color assignment; Computer science; Computer vision; Euclidean distance; Image reconstruction; Image storage; Isosurfaces; Laser modes; Layout; Surface reconstruction; Three dimensional displays;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
3-D Digital Imaging and Modeling, 2003. 3DIM 2003. Proceedings. Fourth International Conference on
Print_ISBN :
0-7695-1991-1
Type :
conf
DOI :
10.1109/IM.2003.1240275
Filename :
1240275
Link To Document :
بازگشت