SIFT-AID: BOOSTING SIFT WITH AN AFFINE INVARIANT DESCRIPTOR BASED ON CONVOLUTIONAL NEURAL NETWORKS

Abstract : The classic approach to image matching consists in the detection , description and matching of keypoints. The descriptor encodes the local information around the keypoint. An advantage of local approaches is that viewpoint deformations are well approximated by affine maps. This motivated the quest for affine invariant local descriptors. Despite numerous efforts, such descriptors remained elusive, ultimately resulting in the compromise of using viewpoint simulations to attain affine invariance. In this work we propose a CNN-based patch descriptor which captures affine invariance without the need for viewpoint simulations. This is achieved by training a neural network to associate similar vectorial representations to patches related by affine transformations. During matching , these vectors are compared very efficiently. The invari-ance to translation, rotation and scale is still obtained by the first stages of SIFT, which produce the keypoints. The proposed descriptor outperforms the state-of-the-art in retaining affine invariant properties.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [30 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02016010
Contributor : Mariano Rodríguez Guerra <>
Submitted on : Tuesday, February 12, 2019 - 3:22:01 PM
Last modification on : Thursday, June 6, 2019 - 1:16:41 AM
Long-term archiving on : Monday, May 13, 2019 - 5:35:24 PM

File

output.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02016010, version 1

Citation

Mariano Rodríguez, Gabriele Facciolo, Rafael Grompone von Gioi, Pablo Musé, Jean-Michel Morel, et al.. SIFT-AID: BOOSTING SIFT WITH AN AFFINE INVARIANT DESCRIPTOR BASED ON CONVOLUTIONAL NEURAL NETWORKS. 2019. ⟨hal-02016010v1⟩

Share

Metrics

Record views

93

Files downloads

131