skip to main content
Idioma:
Primo Search
Clear Search Box
Search in: Busca Geral
Busca Avançada
Busca por Índices

Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions

Vedaldi, Andrea ; Bischof, Horst ; Brox, Thomas ; Frahm, Jan-Michael

Computer Vision - ECCV 2020, 2020, Vol.12354, p.605-621 [Periódico revisado por pares]

Switzerland: Springer International Publishing AG

Sem texto completo

Citações Citado por
  • Título:
    Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions
  • Autor: Vedaldi, Andrea ; Bischof, Horst ; Brox, Thomas ; Frahm, Jan-Michael
  • Assuntos: Image matching ; Neighbourhood consensus ; Sparse CNN
  • É parte de: Computer Vision - ECCV 2020, 2020, Vol.12354, p.605-621
  • Notas: Electronic supplementary materialThe online version of this chapter (https://doi.org/10.1007/978-3-030-58545-7_35) contains supplementary material, which is available to authorized users.
  • Descrição: In this work we target the problem of estimating accurately localized 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 localized correspondences. Our proposed modifications can reduce the memory footprint and execution time more than 10×\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document} 0\times end{document}, 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. localization 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 relocalization module. The proposed Sparse-NCNet method obtains state-of-the-art results on the HPatches Sequences and InLoc visual localization benchmarks, and competitive results on the Aachen Day-Night benchmark.
  • Títulos relacionados: Lecture Notes in Computer Science
  • Editor: Switzerland: Springer International Publishing AG
  • Idioma: Inglês
Voltar para lista de resultados
Ir para página anteriorAnterior Resultado  2 AvançarIr para próxima página

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.