ETH Zurich - D-INFK - IVC - CVG - Research - Consensus Maximization for Semantic Region Correspondences

Consensus Maximization for Semantic Region Correspondences


Pablo Speciale, Danda P. Paudel, Martin R. Oswald,
Hayko Riemenschneider, Luc V. Gool, and Marc Pollefeys

CVPR 2018

Abstract

We propose a novel method for the geometric registration of semantically labeled regions. We approximate semantic regions by ellipsoids, and leverage their convexity to formulate the correspondence search effectively as a constrained optimization problem that maximizes the number of matched regions, and which we solve globally optimal in a Branch-and-Bound fashion. To this end, we derive suitable linear matrix inequality constraints which describe ellipsoid-to-ellipsoid assignment conditions. Our approach is robust to large percentages of outliers and thus applicable to difficult correspondence search problems. In multiple experiments we demonstrate the flexibility and robustness of our approach on a number of challenging vision problems.

Publication

  • Consensus Maximization with Linear Matrix Inequality Constraints.
    P. Speciale, D. P. Paudel, M. R. Oswald, H. Riemenschneider, Luc V. Gool, and Marc Pollefeys.
    Conference on Computer Vision and Pattern Recognition (CVPR, spotlight) 2018.

Video


© CVG, ETH Zürich lm@inf.ethz.ch