Issue No. 08 - Aug. (2012 vol. 34)
L. Agapito , Sch. of Electron. Eng. & Comput. Sci. (EECS), Queen Mary Univ. of London, London, UK
J. Xavier , Inst. for Syst. & Robot. (ISR), Tech. Univ. of Lisbon, Lisbon, Portugal
A. Del Bue , Dept. of the Ist. Italiano di Tecnol., PAVIS, Genova, Italy
M. Paladini , Sch. of Electron. Eng. & Comput. Sci. (EECS), Queen Mary Univ. of London, London, UK
This paper presents a unified approach to solve different bilinear factorization problems in computer vision in the presence of missing data in the measurements. The problem is formulated as a constrained optimization where one of the factors must lie on a specific manifold. To achieve this, we introduce an equivalent reformulation of the bilinear factorization problem that decouples the core bilinear aspect from the manifold specificity. We then tackle the resulting constrained optimization problem via Augmented Lagrange Multipliers. The strength and the novelty of our approach is that this framework can seamlessly handle different computer vision problems. The algorithm is such that only a projector onto the manifold constraint is needed. We present experiments and results for some popular factorization problems in computer vision such as rigid, non-rigid, and articulated Structure from Motion, photometric stereo, and 2D-3D non-rigid registration.
stereo image processing, computer vision, image registration, optimisation, articulated structure, computer vision, bilinear modeling via augmented Lagrange multipliers, BALM, bilinear factorization problems, missing data, constrained optimization, equivalent reformulation, core bilinear aspect, manifold specificity, manifold constraint, 2D-3D nonrigid registration, photometric stereo, rigid structure, nonrigid structure, Manifolds, Optimization, Shape, Three dimensional displays, Computer vision, Nickel, Cameras, image registration., Bilinear optimization, augmented Lagrangian, SfM, photometric stereo
L. Agapito, J. Xavier, A. Del Bue and M. Paladini, "Bilinear Modeling via Augmented Lagrange Multipliers (BALM)," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 1496-1508, 2012.