Convolutional Neural Network Architecture for Geometric Matching

We address the problem of determining correspondences between two images in agreement with a geometric model such as an affine or thin-plate spline transformation, and estimating its parameters. The contributions of this work are three-fold. First, we propose a convolutional neural network architecture for geometric matching. The architecture is based on three main components that mimic the standard steps of feature extraction, matching and simultaneous inlier detection and model parameter estimation, while being trainable end-to-end. Second, we demonstrate that the network parameters can be trained from synthetically generated imagery without the need for manual annotation and that our matching layer…

• CI
  Canadian Institute for Advanced Research
• AN
  Agence Nationale de la Recherche

  Awards: 13-CORD-0003, ANR-13-CORD-0003