EpiLoc: Deep Camera Localization Under Epipolar Constraint

• Luoyuan Xu,
• Tao Guan,
• Yawei Luo,
• Yuesong Wang,
• Zhuo Chen,
• WenKai Liu,

Vol. 16, No. 6, June 30, 2022
10.3837/tiis.2022.06.014, Download Paper (Free):

• Camera localization
• End-to-end
• Epipolar geometry
• Pixel-level constraint.

Abstract

Recent works have shown that the geometric constraint can be harnessed to boost the performance of CNN-based camera localization. However, the existing strategies are limited to imposing image-level constraint between pose pairs, which is weak and coarse-gained. In this paper, we introduce a pixel-level epipolar geometry constraint to vanilla localization framework without the ground-truth 3D information. Dubbed EpiLoc, our method establishes the geometric relationship between pixels in different images by utilizing the epipolar geometry thus forcing the network to regress more accurate poses. We also propose a variant called EpiSingle to cope with non-sequential training images, which can construct the epipolar geometry constraint based on a single image in a self-supervised manner. Extensive experiments on the public indoor 7Scenes and outdoor RobotCar datasets show that the proposed pixel-level constraint is valuable, and helps our EpiLoc achieve state-of-the-art results in the end-to-end camera localization task.

Statistics

Cite this article