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

Armand Zampieri 1 Guillaume Charpiat 2 Yuliya Tarabalka 1
1 TITANE - Geometric Modeling of 3D Environments
CRISAM - Inria Sophia Antipolis - Méditerranée
2 TAU - TAckling the Underspecified
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : We tackle here the problem of multimodal image non-rigid 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.
Complete list of metadatas

Cited literature [38 references]  Display  Hide  Download

https://hal.inria.fr/hal-01718263
Contributor : Guillaume Charpiat <>
Submitted on : Tuesday, February 27, 2018 - 11:31:35 AM
Last modification on : Friday, April 19, 2019 - 4:55:03 PM
Long-term archiving on : Monday, May 28, 2018 - 7:47:10 PM

Identifiers

  • HAL Id : hal-01718263, version 1
  • ARXIV : 1802.09816

Relations

Citation

Armand Zampieri, Guillaume Charpiat, Yuliya Tarabalka. Coarse to fine non-rigid registration: a chain of scale-specific neural networks for multimodal image alignment with application to remote sensing. 2018. ⟨hal-01718263⟩

Share

Metrics

Record views

755

Files downloads

445