Toft, C;
Turmukhambetov, D;
Sattler, T;
Kahl, F;
Brostow, GJ;
(2020)
Single-Image Depth Prediction Makes Feature Matching Easier.
In:
Computer Vision – ECCV 2020.
(pp. pp. 473-492).
Springer Nature: Cham, Switzerland.
Preview |
Text
2008.09497.pdf - Accepted Version Download (26MB) | Preview |
Abstract
Good local features improve the robustness of many 3D re-localization and multi-view reconstruction pipelines. The problem is that viewing angle and distance severely impact the recognizability of a local feature. Attempts to improve appearance invariance by choosing better local feature points or by leveraging outside information, have come with pre-requisites that made some of them impractical. In this paper, we propose a surprisingly effective enhancement to local feature extraction, which improves matching. We show that CNN-based depths inferred from single RGB images are quite helpful, despite their flaws. They allow us to pre-warp images and rectify perspective distortions, to significantly enhance SIFT and BRISK features, enabling more good matches, even when cameras are looking at the same scene but in opposite directions.
| Type: | Proceedings paper |
|---|---|
| Title: | Single-Image Depth Prediction Makes Feature Matching Easier |
| Event: | 16th European Conference ECCV: European Conference on Computer Vision |
| ISBN-13: | 978-3-030-58517-4 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1007/978-3-030-58517-4_28 |
| Publisher version: | https://doi.org/10.1007/978-3-030-58517-4_28 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. |
| Keywords: | Local feature matching, Image matching |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10117260 |
Archive Staff Only
 |
View Item |
