Bilinear Modeling via Augmented Lagrange Multipliers (BALM)

  • Authors:

  • Alessio Del Bue;Joao Xavier;Lourdes Agapito;Marco Paladini

  • Affiliations:

  • Istituto Italiano di Tecnologia, Genova;Technical University of Lisbon, Lisboa;Queen Mary University of London, London;Queen Mary University of London, London

  • Venue:
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Year:
  • 2012

Quantified Score

Hi-index 0.14

Visualization

Abstract

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.