Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

CNN-ASSISTED COVERINGS IN THE SPACE OF TILTS: BEST AFFINE INVARIANT PERFORMANCES WITH THE SPEED OF CNNS

Abstract : The classic approach to image matching consists in the detection, description and matching of keypoints. In the description, the local information surrounding the keypoint is encoded. This locality enables affine invariant methods. Indeed, smooth deformations caused by viewpoint changes are well approximated by affine maps. Despite numerous efforts, affine invariant descriptors have remained elusive. This has led to the development of IMAS (Image Matching by Affine Simulation) methods that simulate viewpoint changes to attain the desired invariance. Yet, recent CNN-based methods seem to provide a way to learn affine invariant descriptors. Still, as a first contribution, we show that current CNN-based methods are far from the state-of-the-art performance provided by IMAS. This confirms that there is still room for improvement for learned methods. Second, we show that recent advances in affine patch nor-malization can be used to create adaptive IMAS methods that select their affine simulations depending on query and target images. The proposed methods are shown to attain a good compromise: on the one hand, they reach the performance of state-of-the-art IMAS methods but are faster; on the other hand, they perform significantly better than non-simulating methods, including recent ones. Source codes are available at https://rdguez-mariano.github.io/pages/adimas.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02494121
Contributor : Mariano Rodríguez <>
Submitted on : Friday, February 28, 2020 - 2:29:34 PM
Last modification on : Thursday, April 15, 2021 - 3:31:53 AM
Long-term archiving on: : Friday, May 29, 2020 - 2:38:00 PM

File

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02494121, version 1

Citation

Mariano Rodríguez, Gabriele Facciolo, Rafael Grompone von Gioi, Pablo Muse, Julie Delon, et al.. CNN-ASSISTED COVERINGS IN THE SPACE OF TILTS: BEST AFFINE INVARIANT PERFORMANCES WITH THE SPEED OF CNNS. 2020. ⟨hal-02494121⟩

Share

Metrics

Record views

93

Files downloads

356