FisheyeSuperPoint: Keypoint Detection and Description Network for Fisheye Images

TL;DR

This paper introduces FisheyeSuperPoint, a novel network tailored for keypoint detection and description in fisheye images, addressing a gap in existing methods primarily designed for standard cameras, and demonstrates its effectiveness on relevant datasets.

Contribution

It presents a new training and evaluation pipeline specifically for fisheye images, adapting SuperPoint for fisheye distortion, and introduces a fisheye-specific evaluation method.

Findings

Enhanced keypoint detection and description on fisheye images.

Improved performance on HPatches and Oxford RobotCar datasets.

Effective adaptation of SuperPoint to fisheye camera distortions.

Abstract

Keypoint detection and description is a commonly used building block in computer vision systems particularly for robotics and autonomous driving. However, the majority of techniques to date have focused on standard cameras with little consideration given to fisheye cameras which are commonly used in urban driving and automated parking. In this paper, we propose a novel training and evaluation pipeline for fisheye images. We make use of SuperPoint as our baseline which is a self-supervised keypoint detector and descriptor that has achieved state-of-the-art results on homography estimation. We introduce a fisheye adaptation pipeline to enable training on undistorted fisheye images. We evaluate the performance on the HPatches benchmark, and, by introducing a fisheye based evaluation method for detection repeatability and descriptor matching correctness, on the Oxford RobotCar dataset.