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.
@article{arxiv.2008.09497,
title = {Single-Image Depth Prediction Makes Feature Matching Easier},
author = {Carl Toft and Daniyar Turmukhambetov and Torsten Sattler and Fredrik Kahl and Gabriel Brostow},
journal= {arXiv preprint arXiv:2008.09497},
year = {2020}
}
Comments
14 pages, 7 figures, accepted for publication at the European conference on computer vision (ECCV) 2020