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

Hugo Germain, Guillaume Bourmaud, Vincent Lepetit

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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 …
Original languageEnglish
Title of host publication2019 International Conference on 3D Vision (3DV)
Pages513-523
Publication statusPublished - 2019

Fingerprint Dive into the research topics of 'Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization'. Together they form a unique fingerprint.

Cite this