Title :
A Globally Optimal Algorithm for Robust TV-L1 Range Image Integration
Author :
Zach, Christopher ; Pock, Thomas ; Bischof, Horst
Author_Institution :
VRVis Res. Center, Vienna
Abstract :
Robust integration of range images is an important task for building high-quality 3D models. Since range images, and in particular range maps from stereo vision, may have a substantial amount of outliers, any integration approach aiming at high-quality models needs an increased level of robustness. Additionally, a certain level of regularization is required to obtain smooth surfaces. Computational efficiency and global convergence are further preferable properties. The contribution of this paper is a unified framework to solve all these issues. Our method is based on minimizing an energy functional consisting of a total variation (TV) regularization force and an L1 data fidelity term. We present a novel and efficient numerical scheme, which combines the duality principle for the TV term with a point-wise optimization step. We demonstrate the superior performance of our algorithm on the well-known Middlebury multi-view database and additionally on real-world multi-view images.
Keywords :
image processing; stereo image processing; Middlebury multiview database; data fidelity; duality principle; global convergence; globally optimal algorithm; high-quality 3D models; point-wise optimization; range image integration; real-world multi-view images; smooth surfaces; stereo vision; total variation regularization; Computational efficiency; Computer graphics; Convergence; Embedded computing; Geometry; Image reconstruction; Robustness; Stereo vision; Surface reconstruction; TV;
Conference_Titel :
Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on
Conference_Location :
Rio de Janeiro
Print_ISBN :
978-1-4244-1630-1
Electronic_ISBN :
1550-5499
DOI :
10.1109/ICCV.2007.4408983