Skip to Main content Skip to Navigation
Conference papers

Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization

Abstract : We propose a novel approach to feature point matching, suitable for robust and accurate outdoor visual localization in long-term scenarios. Given a query image, we first match it against a database of registered reference images, using recent retrieval techniques. This gives us a first estimate of the camera pose. To refine this estimate, like previous approaches, we match 2D points across the query image and the retrieved reference image. This step, however, is prone to fail as it is still very difficult to detect and match sparse feature points across images captured in potentially very different conditions. Our key contribution is to show that we need to extract sparse feature points only in the retrieved reference image: We then search for the corresponding 2D locations in the query image exhaustively. This search can be performed efficiently using convolutional operations , and robustly by using hypercolumn descriptors, i.e. image features computed for retrieval. We refer to this method as 'Sparse-to-Dense Hypercolumn Matching'. Because we know the 3D locations of the sparse feature points in the reference images thanks to an offline reconstruction stage, it is then possible to accurately estimate the camera pose from these matches. Our experiments show that this method allows us to outperform the state-of-the-art on several challenging outdoor datasets.
Complete list of metadata

Cited literature [76 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02353464
Contributor : Guillaume Bourmaud Connect in order to contact the contributor
Submitted on : Thursday, November 7, 2019 - 12:18:33 PM
Last modification on : Saturday, December 4, 2021 - 3:07:17 AM
Long-term archiving on: : Sunday, February 9, 2020 - 12:00:35 AM

File

3DV_2019_Paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02353464, version 1

Citation

Hugo Germain, Guillaume Bourmaud, Vincent Lepetit. Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization. 3DV, Sep 2019, Quebec, Canada. ⟨hal-02353464⟩

Share

Metrics

Record views

107

Files downloads

213