Visual Gyroscope: Combination of Deep Learning Features and Direct Alignment for Panoramic Stabilization

Bruno Berenguel-Baeta, Antoine N. Andre, Guillaume Caron, Jesus Bermudez-Cameo, Jose J. Guerrero
2/2/2024
cs.CV

No official code found. Best implementation: Sbrunoberenguel/HoLiNet (3 stars, GPL-3.0, last commit 2023-06-08).

Abstract

In this article we present a visual gyroscope based on equirectangular panoramas. We propose a new pipeline where we take advantage of combining three different methods to obtain a robust and accurate estimation of the attitude of the camera. We quantitatively and qualitatively validate our method on two image sequences taken with a $360^\circ$ dual-fisheye camera mounted on different aerial vehicles.

View on arXivView PDF

Code Implementations(1)

Sbrunoberenguel/HoLiNetCommunity100%
GPL-3.0
30PythonApr 7, 20233 years agoGPL-3.0

Similar Papers

Toward Efficient Visual Gyroscopes: Spherical Moments, Harmonics Filtering, and Masking Techniques for Spherical Camera Applications

86% match2024

Multi-LVI-SAM: A Robust LiDAR-Visual-Inertial Odometry for Multiple Fisheye Cameras

82% match2025

Dual-Projection Fusion for Accurate Upright Panorama Generation in Robotic Vision

81% match1 repo12025

Relative Pose for Nonrigid Multi-Perspective Cameras: The Static Case

80% match2024

Perspective-Equivariance for Unsupervised Imaging with Camera Geometry

79% match1 repo32024

GeoCalib: Learning Single-image Calibration with Geometric Optimization

79% match2 repos9372026

Cite this paper

@article{berenguelbaeta2024visual,
  title  = {Visual Gyroscope: Combination of Deep Learning Features and Direct Alignment for Panoramic Stabilization},
  author = {Bruno Berenguel-Baeta and Antoine N. Andre and Guillaume Caron and Jesus Bermudez-Cameo and Jose J. Guerrero},
  year   = {2024},
  eprint = {2402.01461},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.01461v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.01461.svg)](https://codeofpaper.com/paper/2402.01461)

Discussion