Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions

Abstract : In this work we target the problem of estimating accurately localised correspondences between a pair of images. We adopt the recent Neighbourhood Consensus Networks that have demonstrated promising performance for difficult correspondence problems and propose modifications to overcome their main limitations: large memory consumption, large inference time and poorly localised correspondences. Our proposed modifications can reduce the memory footprint and execution time more than $10\times$, with equivalent results. This is achieved by sparsifying the correlation tensor containing tentative matches, and its subsequent processing with a 4D CNN using submanifold sparse convolutions. Localisation accuracy is significantly improved by processing the input images in higher resolution, which is possible due to the reduced memory footprint, and by a novel two-stage correspondence relocalisation module. The proposed Sparse-NCNet method obtains state-of-the-art results on the HPatches Sequences and InLoc visual localisation benchmarks, and competitive results in the Aachen Day-Night benchmark.
Type de document :
Communication dans un congrès
Liste complète des métadonnées

Littérature citée [64 références]  Voir  Masquer  Télécharger
Contributeur : Ignacio Rocco <>
Soumis le : lundi 28 septembre 2020 - 10:43:43
Dernière modification le : mardi 29 septembre 2020 - 08:53:17


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-02950617, version 1
  • ARXIV : 2004.10566



Ignacio Rocco, Relja Arandjelovic, Josef Sivic. Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions. ECCV 2020 - 16th European Conference on Computer Vision, Aug 2020, Glasgow / Virtual, United Kingdom. ⟨hal-02950617⟩



Consultations de la notice


Téléchargements de fichiers