[2011.08988] Minimal Solvers for Single-View Lens-Distorted Camera Auto-Calibrationopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

This paper proposes minimal solvers that use combinations of imaged translational symmetries and parallel scene lines to jointly estimate lens undistortion with either affine rectification or focal length and absolute orientation. We use constraints provided by orthogonal scene planes to recover the focal length. We show that solvers using feature combinations can recover more accurate calibrations than solvers using only one feature type on scenes that have a balance of lines and texture. We also show that the proposed solvers are complementary and can be used together in a RANSAC-based estimator to improve auto-calibration accuracy. State-of-the-art performance is demonstrated on a standard dataset of lens-distorted urban images. The code is available at https://github.com/ylochman/single-view-autocalib.

1 mentions: @ducha_aiki
Date: 2020/11/19 23:21

Related Entries

Read more Deep Learning and Computer Vision – Kyiv School of Economics
0 users, 1 mentions 2020/02/24 14:21
Read more [1904.00320] NM-Net: Mining Reliable Neighbors for Robust Feature Correspondencesopen searchopen nav...
0 users, 1 mentions 2020/06/14 23:21
Read more [2007.13172] Learning and aggregating deep local descriptors for instance-level recognitionopen sear...
0 users, 1 mentions 2020/08/02 11:21
Read more How to match images taken from really extreme viewpoints? | Wide baseline stereo meets deep learning...
0 users, 2 mentions 2020/08/06 00:00
Read more [PDF] Depth from Edge and Intensity Based Stereo | Semantic ScholarSemantic Scholar
0 users, 1 mentions 2020/11/24 12:58