Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions

04/22/2020 ∙ by Ignacio Rocco, et al. ∙ 6

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×, 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.



There are no comments yet.


page 2

page 13

page 20

page 22

page 23

page 25

page 27

Code Repositories


Implementation of Sparse-NCNet: "Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions"

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.