Solving Large-Scale Sparse Semidefinite Programs for Combinatorial Optimization
SIAM Journal on Optimization
Quasiconvex Optimization for Robust Geometric Reconstruction
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Multiple View Geometry and the L_"-norm
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Removing Outliers Using The L\infty Norm
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Recovering Camera Motion Using L\infty Minimization
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Sparse Structures in L-Infinity Norm Minimization for Structure and Motion Reconstruction
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Outlier Removal by Convex Optimization for L-Infinity Approaches
PSIVT '09 Proceedings of the 3rd Pacific Rim Symposium on Advances in Image and Video Technology
Deblurring Poissonian images by split Bregman techniques
Journal of Visual Communication and Image Representation
A novel fast method for L∞ problems in multiview geometry
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
| Hi-index | 0.01 |
Globally optimal formulations of geometric computer vision problems comprise an exciting topic in multiple view geometry. These approaches are unaffected by the quality of a provided initial solution, can directly identify outliers in the given data, and provide a better theoretical understanding of geometric vision problems. The disadvantage of these methods are the substantial computational costs, which limit the tractable problem size significantly, and the tendency of reducing a particular geometric problem to one of the standard programs well-understood in convex optimization. We select a view on these geometric vision tasks inspired by recent progress made on other low-level vision problems using very simple (and easy to parallelize) methods. Our view also enables the utilization of geometrically more meaningful cost functions, which cannot be represented by one of the standard optimization problems. We also demonstrate in the numerical experiments, that our proposed method scales better with respect to the problem size than standard optimization codes.