Coarse to fine non-rigid registration: a chain of scale-specific neural networks for multimodal image alignment with application to remote sensing

We tackle here the problem of multimodal image nonrigid registration, which is of prime importance in remote sensing and medical imaging. The difficulties encountered by classical registration approaches include feature design and slow optimization by gradient descent. By analyzing these methods, we note the significance of the notion of scale. We design easy-to-train, fully-convolutional neural networks able to learn scale-specific features. Once chained appropriately, they perform global registration in linear time, getting rid of gradient descent schemes by predicting directly the deformation. We show their performance in terms of quality and speed through various tasks of remote sensing multimodal image alignment. In particular, we are able to register correctly cadastral maps of buildings as well as road polylines onto RGB images, and outperform current keypoint matching methods. Figure 1. Multimodal matching. We align aerial images with cadastral images. Left: original misregistered images, right: after our realignment.