DocumentCode :
1616381
Title :
Generating dense depth maps using a patch cloud and local planar surface models
Author :
Herrera, C. Daniel ; Kannala, Juho ; Heikkilä, Janne
Author_Institution :
Machine Vision Group, Univ. of Oulu, Oulu, Finland
fYear :
2011
Firstpage :
1
Lastpage :
4
Abstract :
Patch cloud based multi-view stereo methods have proven to be an accurate and scalable approach for scene reconstruction. Their applicability, however, is limited due to the semi-dense nature of their reconstruction. We propose a method to generate a dense depth map from a patch cloud by assuming a planar surface model for non-reconstructed areas. We use local evidence to estimate the best fitting plane around missing areas. We then apply a graph cut optimization to select the best plane for each pixel. We demonstrate our approach with a challenging scene containing planar and non-planar surfaces.
Keywords :
computer vision; graph theory; image reconstruction; optimisation; stereo image processing; video signal processing; computer vision; dense depth map generation; graph cut optimization; local planar surface models; multiview stereo methods; patch cloud; scene reconstruction; stereo image processing; Cameras; Image reconstruction; Pixel; Stereo vision; Surface reconstruction; Surface texture; Three dimensional displays; Computer vision; Stereo image processing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON), 2011
Conference_Location :
Antalya
ISSN :
2161-2021
Print_ISBN :
978-1-61284-161-8
Type :
conf
DOI :
10.1109/3DTV.2011.5877169
Filename :
5877169
Link To Document :
بازگشت